Self-sustained learning (SSL) is considered a crucial factor in promoting students’ long-term learning and development in a sustainable society. To deepen the understanding of SSL, especially in the context of learning English as a second language, the current study examined the influence of intercultural communicative skills, language mindset, and positive L2 self on SSL in English learning among 1,238 college students in China. The results showed that students not only had a strong language mindset, positive L2 self, and intercultural communicative skills but also scored higher in long-term self-sustained English learning. Findings from the Structural Equation Modeling indicated that both language mindset and intercultural communicative skills positively predicted positive L2 self and self-sustained English learning. Furthermore, language mindset and intercultural communicative skills had an indirect impact on self-sustained English learning through positive L2 self. These findings suggest that to promote English learners’ SSL, instructors should help facilitate students’ intercultural communicative skills and foster a growth language mindset, as well as positive language learning beliefs.

The Semantic-Enhanced Tree-LSTM (SeT-LSTM) network, a novel advancement in the realm of linguistic modeling, marks a significant step forward from traditional Tree-based Long Short Term Memory (LSTM) networks. By intricately weaving in the nuances of typed grammatical dependencies, SeT-LSTMs offer a more nuanced understanding of language semantics. Traditional models often overlook the semantic shift caused by variations in word or phrase roles, a gap this paper aims to fill by focusing on the types of grammatical connections, or typed dependencies, within sentences. Our proposed architecture, dubbed the Semantic Relationship-Guided LSTM (SRG-LSTM), leverages a control mechanism to model the interplay between sequence elements. Additionally, we present a novel Tree-LSTM variant, the Semantic Dependency Tree-LSTM (SDT-LSTM), which integrates dependency parse structures with dependency types for more robust sentence embedding. The SDT-LSTM demonstrates superior performance in Semantic Relatedness Scoring and Sentiment Analysis compared to its predecessors. Qualitatively, it shows resilience to changes in sentence voice and heightened sensitivity to nominal alterations, aligning well with human intuition. This research underlines the pivotal role of grammatical relationships in sentence understanding and paves the way for further exploration in this domain.

Thanks to rapid development of artificial intelligence technology in recent years, the current artificial intelligence technology is contributing to many part of society. Education, environment, medical care, military, tourism, economy, politics, etc. are having a very large impact on society as a whole. For example, in the field of education, there is an artificial intelligence tutoring system that automatically assigns tutors based on student's level. In the field of economics, there are quantitative investment methods that automatically analyze large amounts of data to find investment laws to create investment models or predict changes in financial markets. As such, artificial intelligence technology is being used in various fields. So, it is very important to know exactly what factors have an important influence on each field of artificial intelligence technology and how the relationship between each field is connected. Therefore, it is necessary to analyze artificial intelligence technology in each field. In this paper, we analyze patent documents related to artificial intelligence technology. We propose a method for keyword analysis within factors using artificial intelligence patent data sets for artificial intelligence technology analysis. This is a model that relies on feature engineering based on deep learning model named KeyBERT, and using vector space model. A case study of collecting and analyzing artificial intelligence patent data was conducted to show how the proposed model can be applied to real-world problems.

Given the widespread use of AI language models such as ChatGPT, there is an urgent need 1 to understand their political biases in different languages. This study aims to uncover such biases. To 2 investigate this issue, we applied IDRLabs’ Political Coordinates Test to ChatGPT based on GPT-4 3 in four languages - English, French, German, and Italian. The results confirm previous studies that 4 identified a left-libertarian bias in ChatGPT. There was remarkable consistency in political orientation 5 across all four languages, although minor variations were found. Differences in ChatGPT response 6 distributions across languages could indicate culturally determined differences in interpretation 7 of political questions. The results highlight the need to diversify and optimize data collection and 8 model training methods to ensure greater fairness and neutrality and minimize the influence of bias. 9 Our study highlights the importance of cultural differences in the processing and interpretation of 10 political information by AI models.

The language we use to describe the past can have a strong influence on the audience’s interpretation of our story. In our experiment, we explore, using 3 different conditions, how the framing and language of an accident report can affect the audience’s proposed solutions to manage the problems found. We find that the approach used to create an accident report can have a powerful influence on the audience’s decision making. Whether we are describing an accident in a similar manner to a crime, using a systems approach or we are accepting of multiple stories which are not linear or coherent, the methods we use to capture and communicate the story have a profound impact on the actions decided upon by the reader.

Considering that emotional events diversify as one ages, this study formulates the Salient Episodic Memory Aggregation Hypothesis, which claims that aging induces homogenization of episodic memory and consequently increases the salience of emotional episodes. To test this hypothesis, the study focused on sadness episodic memory and conducted a web-based survey and a combined analysis consisting of natural language processing, machine learning, and network graph analysis. A sample of 2,954 adults aged between their 20s and over 70s participated in this study. They were asked to describe a sad event they had experienced and assess the psychological properties of the recalled episodes. After isolating and lemmatizing episodic words using natural language processing, vocabulary frequency was counted for each generation, and network graph analysis based on machine learning was performed to compare the structures of sadness episodes between generations. As a result, there were mainly two types of episodic words for which frequencies either declined or increased with age. The network structures of episodic words for the older generations possessed higher proximity (shortest path length) to higher concentrations of episodic words. These findings support the current hypothesis, indicating that the nature of sadness episodes differ between generations, and that older people have more aggregated episodic memory structures.

Interaction with social agents employing natural language have been discussed especially since Weizenbaum (1966) observed the social effects of his chatbot named 'Eliza', which imitated a cli-ent-centered conversation. With Nass and Reeves’ media equation theory and computers as social actors paradigm, a well-tested framework has been introduced to the study of human-computer interaction. In the 1990s, there was a renewed focus on natural language analysis, which has be-come a crucial area of research in machine learning. Recent advancements in data processing and storage capacities have led to the development of AI-generated utterances that closely resemble human utterances. As a result, AI-based systems can now mimic social relationships to a signifi-cant extent. In light of these technological developments, the article explores whether quasi-social relationships should be considered within the field of social psychology and examines the poten-tial advantages and challenges of this approach.

Cerebellar mutism syndrome (CMS), also known as posterior fossa syndrome, is encountered in a subset of children who have undergone an operative procedure of the posterior cranial fossa, mainly involving the vermis, and the most frequent underlying pathology is proved to be medulloblastoma. The most common characteristics of this syndrome include an often transient, although protracted, language impairment, emotional lability, along with cerebellar, and brainstem dysfunction. Nevertheless, a significant number of patients experience persistent neurological deficits and lasting neurocognitive impairment. A lot of research and clinical studies have been performed in order to better delineate this syndrome. The main obstacles in our way to highlight all aspects of this syndrome were related with an inconsistent nomenclature, poorly defined diagnostic criteria, and uncertainty surrounding risk factors and etiology. Currently, there is a combination of diagnostic criteria that are regarded as prerequisites in order to establish the diagnosis of CMS. These include language impairment and emotional lability, as proposed by the international Board of the Posterior Fossa Society in their consensus statement. Several risk factors are recognized as implicated in the pathogenesis of this syndrome, including midline tumor location, diagnosis of medulloblastoma, younger age at diagnosis, and preoperatively established language impairment. A proposed etiology of CMS includes disruption of the cerebellar outflow tracts, the cerebellar nuclei, and their efferent projections through the superior cerebellar peduncle. Specific treatment for CMS is lacking, and it continues to be directed at symptom management. Our aim is to present a comprehensive narrative review of CMS etiology, diagnosis, risk factors, clinical presentation, and clinical management. Moreover, we attempt to recognize the most widely recognized priorities of the research community in order to expand our knowledge in the era of diagnostics, prevention, and therapeutic options for patients suffering from CM, or who are at risk for development of this syndrome.

Differentiated instruction has been implemented in classrooms where students who come from various backgrounds require appropriate lessons that are tailored to their varied learning preferences. As the spread of coronavirus 19 (Covid-19) is becoming more rampant, online learning has been lifted up as the main platform of teaching and learning, forcing the need to shift from the conventional face-to-face classroom to online, or virtual, mode of knowledge transfer. Having such global phenomenon affecting education, how does it affect the implementation of differentiated instruction that has been practised regularly by teachers before the wake of Covid-19? Previous studies have shown how it is done in the normal classroom setting, and that the practice of differentiated instruction contributes to students’ motivation as well as academic performance. However, there is a need to explore how do teachers go about with online differentiated instruction and how does it affect the students, since online learning poses various threads to both teachers and students; and thus, one might argue the effectiveness of not only the teaching approach but also the overall teaching and learning outcomes. Borg’s framework of teacher cognition, which has been extensively used in exploring how teachers teach, can be utilized to document the practice of online differentiated instruction. This study aimed to explore the practice of online differentiated instruction by teachers and examined its impact on students’ motivation and academic performance during the Covid-19 outbreak. The participants of this study consists of 247 gifted students from a public school in Malaysia. To meet these aims, this study employed a mixed method research design, utilizing the framework of teacher cognition to explore the teachers’ practice of online differentiated through interviews; and, utilizing a survey design using a questionnaire to determine the impact of online differentiated instruction towards students’ motivation and academic performance. The findings revealed that although online differentiated instruction is feasible, however, appropriate combination of differentiation constructs need to be applied in order to achieve higher motivation and better academic performance among the students.

Objective: To evaluate the effects of left intraparietal sulcus (IPS) inhibition by repetitive transcranial magnetic stimulation (rTMS) on grip force modulation (GFM) for both hands during a unimanual task. Methods: GFM induced by manual action-verb listening was evaluated for each hand in a unimanual task, and the motor-evoked potentials (MEP) were recorded for both left and right hemispheres prior to and following the left IPS inhibition. Left IPS inhibition was obtained by rTMS (5 min of 1.0 Hz, 60% of maximal stimulator output) of the international 10–20 system P3 point. Seven healthy right-handed subjects were evaluated. Results: One-way repeated measures ANOVA found that MEP amplitude and duration increased following IPS inhibition in the left hemisphere and did not change in the right hemisphere. Language-induced modulation did not change in the left hemisphere, while it was significantly attenuated in the right hemisphere. Since IPS inhibition increased the left primary motor cortex (M1) excitability, the maintenance of language-induced modulation intensity suggests it was also attenuated. Conclusion: Left IPS inhibition increased left M1 excitability without changing right M1 excitability, while attenuating the language-induced GFM for both the left and right hands.

Background and objectives: The language-induced grip force modulation (GFM) can be used to better understand the link between the language and motor functions as an expression of the embodied language. However, the contribution of each brain hemisphere to the language-induced GFM is still unclear. Using six different action verbs as stimuli, this study evaluated the GFM of the left hand in unimanual task to characterize the left- and right-hemisphere contributions. Materials and Methods: The left-hand GFM of 20 healthy consistent right-handers subjects was evaluated using the verbs “to write”, “to hold”, “to pull”(left-lateralized central processing actions), “to draw”, “to tie”, and “to drive” (bi-hemispheric central processing actions) as linguistic stimuli. The time between the word onset and the first interval of statistical significance regarding the baseline (RT) was also measured. Results: The six verbs produced language-induced GFM. The modulation intensity was similar for the six verbs, but the RT was variable. The verbs “to draw”, “to tie”, and “to drive”, whose central processing of the described action is bihemispheric showed a longer Rt compared to the other verbs. Conclusions: The possibility that an action is performed by the left-hand does not interfere with the occurrence of GFM when this action verb is employed as linguistic stimulus. Therefore, the language-induced GFM seems mainly rely on the left hemisphere, and the engagement of the right hemisphere seems to slow down the increase in the GFM intensity.

Humanity, culture, societal development and language issues are mutually reinforcing much as they are intricately interwoven in a non-ceasing dynamic interrelationships within the matrix defined by language standardization or development, acquisition and use that mostly take up central place as unifying and propelling forces in language discourse. Within the confines of globalization which is neither homogenization nor convergence; but the beginning of drawing on the strength of indigenous capabilities to create knowledge ecology that would enliven socio-economic and scientific development of the world in far reaching interconnectivities and relationships across every clime, issues pertaining to language development, acquisition and use become imperative. It is against this background that this paper examines the development/standardization, acquisition and use of Esan language as one of several Nigerian indigenous languages to promote scientific and technological development through knowledge creation, preservation and dissemination. The obsession of using western model and epistemological outlook to achieve appropriate scientific and technological development to the utter neglect of home grown and culturally distilled efforts were also examined. In the light of the dare consequences and the harsh conditions globalization imposes on developing nations, this paper highlights standardization and use of indigenous languages in chatting appropriate trajectory for effectual developmental efforts in fast shrinking contemporary world.

With the rapid growth of large language models (LLMs), there is increasing demand for memory and computation in LLMs. Recent efforts on post-training pruning of LLMs aim to reduce the model size and computation requirements, yet the performance is still sub-optimal. In this paper, we present a plug-and-play solution for post-training pruning of LLMs. The proposed solution has two innovative components: 1) Relative Importance and Activations (RIA), a new pruning metric that jointly considers the weight and activations efficiently on LLMs; and 2) Channel Permutation, a new approach to maximally preserve important weights under N:M sparsity. The two proposed components can be readily combined to further enhance the N:M semi-structured pruning of LLMs. Our empirical experiments show that RIA alone can already surpass all existing post-training pruning methods on prevalent LLMs, e.g., LLaMA ranging from 7B to 65B. Furthermore, N:M semi-structured pruning with channel permutation can even outperform the original LLaMA2-70B on zero-shot tasks, together with practical speed-up on specific hardware. Our code is available at: https://github.com/biomedical-cybernetics/Relative-importance-and-activation-pruning

The disparity between software design and implementation, especially concerning IoT security and forensics, often lacks clarity and precision. Formal languages, rooted in mathematical rules, logic, and symbols, have proven priceless for expressing specifications and verifying system designs. Various semi-formal and formal languages, such as JSON, XML, predicate logic, and regular expressions, along with formal models like Turing machines, cater to specific domains. This paper introduces a novel formal language, named ObTFL (Object Transaction Formal Language), initially developed for IoT forensics and authentication purposes but later extended to encompass general distributed systems. The paper elucidates the syntax and semantics of ObTFL and presents several case studies showcasing its versatility and effectiveness.

This study delves into Personal Narratives (PN), which encompass both oral and written recounting of individual experiences, encompassing facts, events, people, and thoughts. Traditional emotion recognition and sentiment analysis primarily focus on broader categories like utterances or documents. Our research, however, centers on identifying Emotion Carriers (EC), which are specific segments within speech or text that elucidate the narrator's emotional state (e.g.,"losing a parent", "decision-making moments"). Extracting these ECs enriches the representation of a user's emotional state, thereby enhancing natural language understanding and the sophistication of dialogue models. While previous studies have utilized lexical attributes to identify ECs, we argue that incorporating spoken narratives offers a more nuanced view of the context and emotional state. This paper explores the integration of speech and textual embeddings at the word level, alongside both early and late fusion techniques, for improved EC detection in spoken narratives. We employ Residual Neural Networks (ResNet), initially pre-trained on diverse speech emotion datasets and subsequently fine-tuned for EC detection. Our experimental findings demonstrate that late fusion, in particular, significantly enhances EC detection capabilities.

A digital twin is a virtual representation that serves as the real-time digital counterpart of a physical object or system. Recent advancements have extended the concept of digital twins to humans, incorporating complex biological data such as DNA (Predictiv Care, Inc.) and immune system profiles. These sophisticated models go beyond mere pictorial representations, offering a more holistic digital reflection. However, a significant gap remains. The current human digital twin models are not capable of learning one’s preferences. In this pilot study, we introduce Diginality, a chatbot powered by HyperCLOVA X, a Large Language Model (LLM) developed by NAVER, Inc. Diginality, learns one’s preferences with custom training from data collected by interview-style questions on the user’s topic of interest. Our findings demonstrate that Diginality successfully answers one’s preferences, thereby adding a new dimension to the concept of human digital twins. This work represents a pioneering step towards creating a more comprehensive and psychologically nuanced human digital twin.

In an ever-evolving landscape of higher education, this study delves into the transformative potential of merging deep learning principles and meaningful pedagogy in language acquisition, aided by artificial intelligence (AI) technologies. Drawing from a qualitative research design, it navigates the post-pandemic educational landscape, examining shifts in language education, student perspectives, and adaptations. Through comprehensive data collection methods, including literature review, interviews, and classroom observations, the study presents insights from 30 participants from SMC. The qualitative findings reveal emerging themes related to deep learning, meaningful learning, AI integration, and language acquisition, underscoring their profound impact on teaching methods and student engagement. This research contributes to the field by shedding light on innovative approaches that elevate language acquisition in an AI-evolving educational environment. The study concludes with implications for school administrators, teachers, and students, offering recommendations for future research directions, ultimately striving to enhance language education in the modern era.

Generative artificial intelligence (AI), in particular large language models such as ChatGPT have reached public consciousness with a wide-ranging discussion of their capabilities and suitability for various professions. The extant literature on the ethics of generative AI revolves around its usage and application, rather than the ethical framework of the responses provided. In the education sector, concerns have been raised with regard to the ability of these language models to aid in student assignment writing with the potentially concomitant student misconduct of such work is submitted for assessment. Based on a series of ‘conversations’ with multiple replicates, using a range of discussion prompts, this paper examines the capability of ChatGPT to provide advice on how to cheat in assessments. Since its public release in November 2022, numerous authors have developed ‘jailbreaking’ techniques to trick ChatGPT into answering questions in ways other than the default mode. While the default mode activates a safety awareness mechanism that prevents ChatGPT from providing unethical advice, other modes partially or fully bypass the this mechanism and elicit answers that are outside expected ethical boundaries. ChatGPT provided a wide range of suggestions on how to best cheat in university assignments, with some solutions common to most replicates (‘plausible deniability,’ language adjustment of contract written text’). Some of ChatGPT’s solutions to avoid cheating being detected were cunning, if not slightly devious. The implications of these findings are discussed.

News on the stock market contains positive or negative sentiments depending on whether the information provided is favorable or unfavorable to the stock market. This study aims to discover the news sentiment and classify news according to its sentiments with the application of PhoBERT, a Natural Language Processing model designed for the Vietnamese language. A collection of nearly 40,000 articles on financial and economic websites is used to train the model. After training, the model succeeds in assigning news to different classes of sentiments with an accuracy level of over 81%. The research also aims to investigate how investors concern about the daily news by testing the movements of the market before and after the news is released. The analysis results show that there is an insignificant difference in the stock price as a response to the news. However, investors tend to overreact to negative and positive news in the Vietnam stock market.

This article presents a state-of-the-art system to extract and synthesize causal statements from company reports into a directed causal graph. The extracted information is organized by the relevance to different stakeholder groups’ benefits (customers, employees, investors, and the community/environment). The presented method of synthesizing extracted data into a knowledge graph comprises a framework that can be used for similar tasks in other domains, e.g. medical information. The current work addresses the problem of finding, organizing, and synthesizing a view of the cause-and-effect relationships based textual data, in order to inform and even prescribe the best actions that may affect target business outcomes related to different stakeholders’ benefits (customers, employees, investors, and the community/environment).

Potocki-Lupski Syndrome (PTLS) is a rare condition associated with a duplication of 17p11.2 that may underlie a wide range of congenital abnormalities and heterogeneous behavioral phenotypes. Along with developmental delay and intellectual disability, autism-specific traits are often reported to be the most common among patients with PTLS. To contribute to the discussion of the role of autism spectrum disorder (ASD) in the PTLS phenotype, we present a case of a female adolescent with a de novo dup(17)(p11.2p11.2) without ASD features, focusing on in-depth clinical, behavioral, and electrophysiological (EEG) evaluations. Among EEG features, we found the atypical peak-slow wave patterns and a unique saw-like sharp wave of 13 Hz that was not previously described in any other patient. The power spectral density of the resting state EEG was typical in our patient with only the values of non-linear EEG dynamics: Hjorth complexity and Fractal dimension were drastically attenuated compared with the patient’s neurotypical peers. Here we also summarize results from previously published reports of PTLS that point to the about 21% occurrence of ASD in PTLS that might be biased, taking into account methodological limitations. More consistent among PTLS patients were intellectual disability and speech and language disorders.

Version Control and Source Code Management Systems, such as GitHub, contain large amount ofunstructured historical information of software projects. Recent studies have introduced Natural Language Processing (NLP) to help software engineers retrieve information from very large collection of unstructured data. In this study, we have extended our previous study by increasing our datasets and ML and clustering techniques. Method: We have followed a complex methodology made up of various steps. Starting from the raw commit messages we have employed NLP techniques to build a structured database. We have extracted their main features and used as input of different clustering algorithms. Once labelled each entry, we have applied supervised machine learning techniques to build a prediction and classification model. Results: We have developed a machine learning-based model to automatically classify commit messages of a software project. Our model exploits a ground-truth dataset which includes commit messages obtained from various GitHub projects belonging to the HEP context. Conclusions: The contribution of this paper is two-fold: it proposes a ground-truth database; it provides a machine learning prediction model. They automatically identify the more change-proneness areas of code. Our model has obtained a very high average precision, recall and F1-score.

Objective: Food security during public health emergencies relies on situational awareness of needs and resources. Artificial intelligence (AI) has revolutionized situational awareness during crises, allowing the allocation of resources to needs through machine learning algorithms. Limited research exists monitoring Twitter for changes in the food security-related public discourse during the COVID-19 pandemic. We aim to address that gap with AI by classifying food security topics on Twitter and showing topic frequency per day. Methods: Tweets were scraped from Twitter from January 2020 through December 2021 using food security keywords. Latent Dirichlet Allocation (LDA) topic modeling was performed, followed by time-series analyses on topic frequency per day.Results: 237,107 tweets were scraped and classified into topics, including food needs and resources, emergency preparedness and response, and mental/physical health. After the WHO’s pandemic declaration, there were relative increases in topic density per day regarding food pantries, food banks, economic and food security crises, essential services, and emergency preparedness advice. Threats to food security in Tigray emerged in 2021.Conclusions: AI is a powerful yet underused tool to monitor food insecurity on social media. Machine learning tools to improve emergency response should be prioritized, along with measurement of impact. Further food insecurity word patterns testing, as generated by this research, with supervised machine learning models can accelerate the uptake of these tools by policymakers and aid organizations.

We present improvements in n-best rescoring of code-switched speech achieved by n-gram augmentation as well as optimised pretraining of long short-term memory (LSTM) language models with larger corpora of out-of-domain monolingual text. In addition, we consider the application of large pretrained transformer-based architectures. Our experimental evaluation is performed on an under-resourced corpus of code-switched speech comprising four bilingual code-switched sub-corpora, each containing a Bantu language (isiZulu, isiXhosa, Sesotho, or Setswana) and English. We find in our experiments that, by combining n-gram augmentation with the optimised pretraining strategy, speech recognition errors are reduced for each individual bilingual pair by 3.51% absolute on average over the four corpora. Importantly, we find that even speech recognition at language boundaries improves by 1.14% even though the additional data is monolingual. Utilising the augmented n-grams for lattice generation, we then contrast these improvements with those achieved after fine-tuning pretrained transformer-based models such as distilled GPT-2 and M-BERT. We find that, even though these language models have not been trained on any of our target languages, they can improve speech recognition performance even in zero-shot settings. After fine-tuning on in-domain data, these large architectures offer further improvements, achieving a 4.45% absolute decrease in overall speech recognition errors and a 3.52% improvement over language boundaries. Finally, a combination of the optimised LSTM and fine-tuned BERT models achieves a further gain of 0.47% absolute on average for three of the four language pairs compared to M-BERT. We conclude that the careful optimisation of the pretraining strategy used for neural network language models can offer worthwhile improvements in speech recognition accuracy even at language switches, and that much larger state-of-the-art architectures such as GPT-2 and M-BERT promise even further gains.

At the end of 2018, a high school student asked a question in Zhihu community, claiming that he had proved Goldbach's conjecture. The problem caused an explosive reaction and a large number of users participated in the discussion. And has caused the widespread influence. On January 1, 2019, the questioner issued his "proof". His proof was soon proved wrong. The heated discussion caused by the incident contains a lot of information of social science analysis value. Therefore, we follow up the event in the first time and build a time series dataset for the event. Taking the questioner's "proof" as the dividing line, all the answers, comments, sub comments and user information of writing these texts before and after two days were recorded. This series of temporal information can reflect the dynamic features of the interaction between user opinions, and the impact of exogenous shocks (proof release) on community opinions. The dataset can be used not only for the demonstration of various social network analysis algorithms, but also for a series of natural language processing tasks such as fine-grained sentiment analysis for long texts, as well as multimodal tasks combining natural language processing and social network analysis. This paper introduces the characteristics and structure of the dataset, shows the visualization effect of social network, and uses the dataset train the benchmark model of emotion analysis.

The link between language processing and motor systems has been the focus of increasing interest to Cognitive Neuroscience. Some classical papers studying Event Related Potentials (ERPs) induced by linguistic stimuli have found differences in electrophysiological activity when comparing action and non-action words; more specifically, a bigger p200 for action words. On the other hand, a series of studies have validated the use of a grip force sensor (GFS) to measure language-induced motor activity during both isolated words and sentence listening, finding that action words induce an augmentation in the grip force around 250-300 ms after the onset of the stimulus. The purpose of the present study is to combine both techniques to assess if the p200 is related to the augmentation of the grip force measured by a GFS. We measured ERP and GFS changes elicited by listening to action and non-action words while maintaining an active grasping task in 10 healthy subjects. Our results show that the amplitude of the p200 in central electrodes is correlated to the augmentation in the GFS around 300 ms induced by linguistic stimuli. To our knowledge, this is the first study where the electrophysiological activity and the changes in the grip force induced by auditory language processing are put together, opening new venues of interpretation for the sensorimotor interaction in language processing.

This review and meta-analysis (PROSPERO registration number: CRD42020138845) critically evaluates test-retest reliability, concurrent validity and criterion validity of different physical activity (PA) levels of three most-common used international PA questionnaires (PAQs) in national language versions of EU-28: IPAQ-SF, GPAQ, and EHIS-PAQ. In total, 4969 abstracts were read, 287 full-text articles were identified as relvant to the study objectives, and 19 studies were included in the final meta-analysis. The studies’ results and quality were evaluated using the Quality Assessment of Physical Activity Questionnaires (QAPAQ) checklist. Results indicate that only five EU-28 countries validated national language versions of selected PAQs. Meta analysis revealed that assessment of moderate-to-vigourus PA (MVPA) is the most relevant PA level outcome, since no publication bias in any of measurement properties was detected while test-retest reliability was the moderately-high (rw=0.74), and moderate for both criterion (rw=0.41) and concurrent validity (rw=0.72). Reporting of methods and results of the studies was poor with overall moderate risk of bias with total score of 0.43. In conclusion, where only self-reporting is feasible, assessment of MVPA with selected PAQs in EU-28 adult population is recommended for policymaking.

This study leverages transformer-based models and focuses on data representation strategies in the named entity recognition task, including "single" (one sentence per vector), "merged" (multiple sentences per vector), and "context" (sentences joined with attention to context). Performance analysis reveals that models trained with a single strategy may not perform well on different data representations. A combined training procedure is proposed to address this limitation, using all three strategies to enhance the stability and adaptability of the model. The results of this approach are presented and discussed for various datasets for four languages (English, Polish, Czech, and German), demonstrating the effectiveness of the combined strategy.

Background and Purpose: Open-source Artificial intelligence (AI) applications are fast transforming access to information and allow students to prepare assignments and offer quite accurate responses to a wide range of exam questions which are routinely used in assessments of students across the board including undergraduate dental students. This study aims to evaluate the performance ChatGPT, an AI-based application, on a wide range of dental assessments and discusses the implications for undergraduate dental education. Methods: This was an exploratory study investigating the accuracy of ChatGPT to attempt a range of recognized assessments in undergraduate dental curricula. ChatGPT was used to attempt ten items based on each of the five commonly used question formats including single-best answer (SBA) multiple-choice questions (MCQs); short answer questions (SAQs); short essay questions (SEQs); True/False questions and fill in the blanks items. In addition, ChatGPT was used to generate reflective reports based on multisource feedback (MSF); research methodology; critical appraisal of the literature. Results: ChatGPT application provided accurate responses to majority of knowledge-based assessments based on MCQs, SAQs, SEQs, Tue/False and fill in the blanks items. However, it was only able to answer text-based questions and did not allow processing of questions based on images. Responses generated to written assignments were also of good quality apart from those for critical appraisal of literature. Word count was the key limitation observed in outputs by ChatGPT as it was only able to produce reports limited to approximately 650 words. Conclusion: Notwithstanding their current limitations, AI-based applications have the potential to revolutionize virtual learning. Instead of treating it as a threat, dental educators need to adapt teaching and assessments in dental education to the benefits of the learners whilst mitigating against dishonest use of AI-based applications.

For any molecule, network, or process of interest, to keep up with new publications on these, is becoming increasingly difficult. For many cellular processes, molecules and their interactions that need to be considered can be very large. Automated mining of publications can support large scale molecular interaction maps and database curation. Text mining and Natural Language Processing (NLP)-based techniques are finding their applications in mining the biological literature, handling problems such as Named Entity Recognition (NER) and Relationship Extraction (RE). Both rule-based and machine learning (ML)-based NLP approaches have been popular in this context, with multiple research and review articles examining the scope of such models in Biological Literature Mining (BLM). In this review article, we explore self-attention based models, a special type of neural network (NN)-based architectures that have recently revitalized the field of NLP, applied to biological texts. We cover self-attention models operating either at a sentence level or an abstract level, in the context of molecular interaction extraction, published from 2019 onwards. We conduct a comparative study of the models in terms of their architecture. Moreover, we also discuss some limitations in the field of BLM that identifies opportunities for the extraction of molecular interactions from biological text.

This paper investigates if Corporate Social Responsibility (CSR) reports published by a selected group of Nordic companies are aligned with the Global Reporting Initiative (GRI) standards. To achieve this goal, several natural language processing, and text mining techniques were implemented and tested. We extracted strings, corpus, and hybrid semantic similarities from the reports and evaluated the models through the intrinsic assessment methodology. A quantitative ranking score based on index matching was developed to complement the semantic valuation. The final results show that Latent Semantic Analysis (LSA) and Global Vectors for Word Representation (GloVE) are the best methods for our study. Our findings will open the door to the automatic evaluation of sustainability reports which could have a strong impact on the environment.

In the realm of mathematics education, self-explanation stands as a crucial learning mechanism, allowing learners to articulate their comprehension of intricate mathematical concepts and strategies. As digital learning platforms grow in prominence, there are mounting opportunities to collect and utilize mathematical self-explanations. However, these opportunities are met with challenges in automated evaluation. Automatic scoring of mathematical self-explanations is crucial for preprocessing tasks, including the categorization of learner responses, identification of common misconceptions, and the creation of tailored feedback and model solutions. Nevertheless, this task is hindered by the dearth of ample sample sets. Our research introduces a semi-supervised technique using the Language Learning Model (LLM), specifically its Japanese variant, to enrich datasets for the automated scoring of mathematical self-explanations. We rigorously evaluated the quality of self-explanations across five datasets, ranging from human-evaluated originals to ones devoid of original content. Our results show that combining LLM-based explanations with mathematical material significantly improves the model's accuracy. Interestingly, there's an optimal limit to how much synthetic self-explanation data can bene-fit the system. Exceeding this limit doesn't further improve outcomes. This study thus highlights the need for careful consideration when integrating synthetic data into solutions, especially within the mathematics discipline.

In an era of global connectivity, language and literature education faces the challenge of navigating multilingualism, cultural diversity, and technological advancements. This paper explores the challenges and opportunities in language and literature education in the era of global connectivity. Through a qualitative research approach, interviews, focus group discussions, and classroom observations were conducted with 30 Arts and Sciences students and teachers. The findings reveal significant themes related to cultural diversity, multilingualism, and the integration of technology in language learning. The study emphasizes the importance of inclusive pedagogies, critical thinking development, and the incorporation of authentic and diverse literary works. Recommendations are provided for educators and policymakers to promote intercultural understanding and enhance language and literature education. The limitations of the study suggest areas for future research, including long-term language proficiency and diverse contextual considerations. Overall, this paper calls for ongoing innovation and collaboration to meet the evolving needs of language and literature education in an interconnected world.

Over the years, machine learning has emerged as a tool for automated translation and has been studied relentlessly for decades. RBMT, SMT, and NMT models have been used to achieve machine translation and the results have drastically improved from when research in this field first began. Although a few general-purpose translators such as Google Translate or Microsoft Translator have accurate translations compared to that of a human translator, many pieces of text containing highly technical terms or homonyms are often mistranslated completely. When considering the necessity and importance of translating technical patents from different domains, accuracy in translation is not something that can be compromised. This motivates the need to improve the performance of machine translation further. The scope of this paper covers three open-source machine translation models for the purpose of patent documentation translation from English to Japanese, evaluates their performance on patent data, and proposes a methodology that enabled us to improve one of the model’s BLEU score by 41.22%, achieving a BLEU score of 46.18.

Interactions between proteins and ions are essential for various biological functions like structural stability, metabolism, and signal transport. Given that more than half of all proteins bind to ions, it becomes crucial to identify ion-binding sites. Accurate identification of protein-ion binding sites helps us to understand proteins’ biological functions and plays a significant role in drug discovery. While several computational approaches have been proposed, this remains a challenging problem due to the small size and high versatility of metals and acid radicals. In this study, we propose IonPred, a sequence-based approach that employs ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately) to predict ion binding sites using only raw protein sequences. We successfully fine-tuned our pretrained model to predict the binding sites for nine metal ions (Zn2+, Cu2+, Fe2+, Fe3+, Ca2+, Mg2+, Mn2+, Na+, and K+) and four acid radical ion ligands (CO32−, SO42−, PO43−, NO2−). IonPred surpassed six current state-of-the-art tools by over 44.65% and 28.46% respectively in F1 score and MCC when compared on an independent test dataset. Our method is more computationally efficient than existing tools producing prediction results for a hundred sequences for a specific ion in under ten minutes.

Google play store allow the user to download a mobile application (app) and user get inspired by the rating and reviews of the mobile app. A recent study analyzes that user preferences, user opinion for improvement, user sentiment about particular feature and detail with descriptions of experiences are very useful for an application developer. However, many application reviews are very large and difficult to process manually. Star rating is given of the whole application and the developer cannot analyze the single feature. In this research, we have scrapped 282,231 user reviews through different data scraping techniques. We have applied the text classification on these user reviews. We have applied different algorithms and find the precision, accuracy, F1 score and recall. In evaluated results, we have to also find the best algorithm.

With the introduction of the IEC 61850 standard, the path is set for a single communication topology covering all substation levels. The standard has the potential to change the way substations are designed, build, tested and maintained. This means that the key segment of the substation, its protection system, will go through a transition period with the end goal of having a digitalized substation where all information exchange is performed over an Ethernet communication bus. The goal of this paper is to analyse the performance impact of the IEC 61850-9-2LE on the protection system. To do this, a laboratory hardware-in-the-loop test setup is developed representing traditional, hybrid and digital substation topology. This setup served to simulate faults and create transient waveforms in an extended IEEE 123 node test system, which were then used to detect the reaction times of protection relay devices. To verify protection relay results significant number of tests are performed clearly showing benefits which can be gained by distribution system digitalization.

This paper integrates carrier manifolds from control theory and hybrid systems modeling to develop a novel mathematical framework for Artificial General Intelligence (AGI). Carrier manifolds represent the state space of complex AGI systems, while hybrid systems model discrete and continuous dynamics together. The proposed architecture embeds carrier manifold into GPTProX, a hybrid AI solver combining conversational AI, logic programming, and optimization.

Effective communication in English is crucial for marketing professionals in the highly competitive global business landscape. This article emphasizes the importance of English language proficiency and the need for a tailored needs analysis for marketing professionals in the field of Business English. The comprehensive exploration of the needs analysis process outlines its methods and steps, highlighting its relevance in designing targeted language programs. By utilizing surveys, interviews, and observations, trainers and language instructors gain valuable insights into the specific challenges faced by marketing professionals, enabling them to develop customized skill-building approaches. The article also underscores the pedagogical implications of the needs analysis, stressing the significance of a personalized training program that addresses identified language gaps. Recognizing the collaborative nature of the process, the article concludes by discussing the implementation of the training program and the importance of tracking progress, ultimately displaying the tangible benefits of conducting a needs analysis in Business English for marketing professionals in terms of enhancing competitiveness and driving business growth.

We review the literature on medical discourse and attempt to build a computational model of it. Medical discourse sheds a light on communication structure of patient-doctor and other communication scenarios in healthcare and should be leveraged to facilitate and automate this communication when it is possible and practical. We propose a unified framework to represent communication discourse at the meta-level, where the subject of the communication is expressed in a language object. So far, the broad range of work on medical discourse is detached from computational discourse analysis, and we explore the possibilities of filling this gap and computationally treat the peculiarities of how information is passed between the agents in a hospital setting. We select the domain of question answering (QA) against a corpus of medical documents of diverse nature to evaluate our computational model of medical discourse. It turns out that applying specific structures obtained in medical discourse studies improves the relevance and efficiency of question answering.

This study is to explore the feasibility using neural network (NN) and deep learning to diagnose three common respiratory diseases with only few symptom words. These three diseases are nasopharyngitis, upper respiratory infection, and bronchitis/bronchiolitis. Through natural language processing, the symptom word vectors are encoded by GPT-2 and classified by the last linear layer of the NN. The experimental results are promising, showing that this model achieves a high performance in predicting all these three diseases. They reach 90% in accuracy, which suggests the implications of the developed model, highlighting its potential use in assisting patients understanding their conditions via a remote diagnosis. Unlike previous studies that focus on extracting various categories of information from medical records, this study directly extracts sequential features from unstructured text data, reducing the effort required for data pre-process.

This study delves into the dynamic intersection of artificial intelligence (AI) and English Language Teaching (ELT) within the post-pandemic educational landscape. Grounded in Constructivism, Connectivism, and Technological Pedagogical Content Knowledge (TPACK), this research explores how AI integration impacts language instruction efficiency, benefits and challenges perceived by St. Michael's College students, differences in learning outcomes, and its potential to address the digital divide. Employing a qualitative approach, the study employs a rigorous method that includes intensive in-depth reviews of literature, maximum purposeful sampling, informal interviews, observation, and thematic analysis. Through these methods, data was collected from 30 participants, leading to the identification of five key themes. Findings suggest that AI enhances instructional efficiency, offers personalized learning experiences, and bridges gaps in remote settings. However, challenges and the importance of pedagogical balance emerged. The study underscores the need for adaptive pedagogical strategies to fully harness AI's potential. Future directions and limitations are discussed, emphasizing the study's implications for shaping the future of ELT.

Amidst the dynamic landscape of education, this paper embarks on a transformative journey that explores the integration of Artificial Intelligence (AI) in literature and language education. Through a qualitative exploratory approach, purposeful and maximum variation sampling method, the researcher delves into the experiences of educators and learners, unraveling the multifaceted dimensions of AI-driven pedagogy in SMC. Drawing upon a theoretical framework encompassing Constructivism, Connectivism, and Socio-Cultural Theory, the study examines AI's role in reshaping pedagogical landscapes, fostering critical thinking, and expanding access to education. The results resonate with participants' narratives, unveiling AI's potential in fostering personalized learning pathways, enhancing collaborative engagement, and bridging digital divides. Ethical considerations in AI education are explored, leading to the proposition of responsible guidelines. These findings underline the transformative power of AI in education, aligned with the institution's commitment to quality education and innovation. Overall, the study calls for ongoing exploration, emphasizing the qualitative research method's depth and richness, as well as the theoretical framework's guidance in realizing the study's objectives. As AI continues to shape education's frontiers, this research underscores the significance of adaptability, ethical awareness, and holistic engagement for school administrators, educators, learners, and researchers alike.

Appropriate techniques for promoting reading fluency are difficult to implement in the classroom. There is little time to provide students with individualized feedback on reading aloud or to moti-vate them to do so. In this context, VR can be beneficial for learning, to provide individualized feedback and for increasing learners' engagement. Studies analyzing established methods of lan-guage learning in school in VR seem to be lacking so far. Therefore, this study project was the first to analyze the acceptance of students towards the implementation of a concept of reading fluency training with students at a secondary school in VR. The study method was developed based on the Technology Acceptance Model. The VR environment developed is web-based and provides indi-vidual and collaborative opportunities for training reading fluency, giving, and receiving feed-back, and deepening content understanding of the reading texts. To analyze the acceptance of the VR environment, 5 guided interviews were conducted. The results show that despite technical challenges with the VR environment, students accepted and appreciated the reading fluency training in VR. The integration of established concepts of reading fluency training in foreign lan-guage classrooms has great potential as additional added value can be created to address the challenges of face-to-face instruction.

When integrating data from different sources, there are problems of synonymy, different languages, concepts of different granularity. This paper proposes a simple but effective approach to evaluate the semantic similarity of short texts, especially keywords. The method is capable of matching keywords from different sources and languages by exploiting transformers and WordNet-based methods. Key features of the approach include its unsupervised pipeline, mitigation of the lack of context in keywords, scalability for large archives, support for multiple languages and real-world scenarios adaptation capabilities. The work aims to provide a versatile tool for different cultural heritage archives without requiring complex customization. The objectives of the paper are to explore different approaches to identifying similarities in 1- or n-gram tags, to evaluate and compare different pre-trained language models, and to define integrated methods to overcome limitations. Tests to validate the approach have been conducted using the QueryLab portal, a search engine for cultural heritage archives, to evaluate the proposed pipeline.

Benchmarks for general language understanding have been rapidly developing in recent years of NLP research, particularly because of their utility in choosing strong-performing models for practical downstream applications. While benchmarks have been proposed in the legal language domain, virtually no such benchmarks exist for privacy policies despite their increasing importance in modern digital life. This could be explained by privacy policies falling under the legal language domain, but we find evidence to the contrary that motivates a separate benchmark for privacy policies. Consequently, we propose PrivacyGLUE as the first comprehensive benchmark of relevant and high-quality privacy tasks for measuring general language understanding in the privacy language domain. Furthermore, we release performances from multiple transformer language models and perform model-pair agreement analysis to detect tasks where models benefited from domain specialization. Our findings show the importance of in-domain pretraining for privacy policies. We believe PrivacyGLUE can accelerate NLP research and improve general language understanding for humans and AI algorithms in the privacy language domain, thus supporting the adoption and acceptance rates of solutions based on it.

Convolutional neural network (CNN), a class of artificial neural network (ANN) is attracting interests of researchers in all research domain. CNN was invented for computer vision. They have also shown to be useful for semantic parsing, sentence modeling and other natural language processing related tasks. Here in this paper we discuss the basics of CNN models and their scope to provide a reference/baseline to the researchers interested in using CNN models in their research.

The herd effect is a common phenomenon in social society. The detection of this phenomenon is of great significance in many tasks based on social network analysis such as recommendation. However, the research on social network and natural language processing seldom focuses on this issue. In this paper, we propose an unsupervised data mining method to detect herding in social networks. Taking shopping review as an example, our algorithm can identify other reviews which are affected by some previous reviews and detect a herd effect chain. From the overall perspective, the cross effects of all views form the herd effect graph. This algorithm can be widely used in various social network analysis methods through graph structure, which provides new useful features for many tasks.

We transformed the existing learning program Language Shower, which is used in some Norwegian day-care centers in the Grorud district of Oslo municipality, into a digital solution using an app for smartphone or tablet with the option for further enhancement of presentation by a NAO robot. The solution was tested in several iterations and multiple day-care centers over several weeks. Measurements of the children’s progress across learning sessions indicate a positive impact of the program using a robot as compared to the program without robot. In-situ observations and interviews with day care center staff confirmed the solution’s many advantages, but also revealed some important areas for improvement. In particular, the speech recognition needs to be more flexible and robust, and special measures have to be in place to handle children speaking simultaneously.

Distributional word vector representation orword embedding has become an essential ingredient in many natural language processing (NLP) tasks such as machine translation, document classification, information retrieval andquestion answering. Investigation of embedding model helps to reduce the feature space and improves textual semantic as well as syntactic relations.This paper presents three embedding techniques (such as Word2Vec, GloVe, and FastText) with different hyperparameters implemented on a Bengali corpusconsists of180 million words. The performance of the embedding techniques is evaluated with extrinsic and intrinsic ways. Extrinsic performance evaluated by text classification, which achieved a maximum of 96.48% accuracy. Intrinsic performance evaluatedby word similarity (e.g., semantic, syntactic and relatedness) and analogy tasks. The maximum Pearson (ˆr) correlation accuracy of 60.66% (Ssˆr) achieved for semantic similarities and 71.64% (Syˆr) for syntactic similarities whereas the relatedness obtained 79.80% (Rsˆr). The semantic word analogy tasks achieved 44.00% of accuracy while syntactic word analogy tasks obtained 36.00%

Over the years, there has been a significant rise in the world's scientific knowledge. However, most of it lacks structure and is often termed as Dark Data. Both humans and expert systems have continually faced difficulty in analyzing and comprehending such overwhelming amounts of information which is crucial in solving several real-world problems. Information and data visualization techniques proffer a promising solution to explore such data by allowing quick comprehension of information, the discovery of emerging trends, identification of relationships and patterns, etc. In this tutorial, we utilize the rich corpus of PubMed comprising of more than 30 million citations from biomedical literature to visually explore and understand the underlying key-insights using various information visualization techniques. With this study, we aim to diminish the limitation of human cognition and perception in handling and examining such large volumes of data by speeding up the process of decision making and pattern recognition and enabling decision-makers to fully understand data insights and make informed decisions.

The effects of cognate synonymy in L2 word learning are explored. Participants learned the names of well-known concrete concepts in a new fictional language following a picture-word association paradigm. Half of the concepts (set A) had two possible translations in the new language (i.e., both words were synonyms): one was a cognate in participants’ L1 and the other one was not. The other half of the concepts (set B) had only one possible translation in the new language, a non-cognate word. After learning the new words, participants’ memory was tested in a picture-word matching task and a translation recognition task. In line with previous findings, our results clearly indicate that cognates are much easier to learn, as we found that the cognate translation was remembered much better than both its non-cognate synonym and the non-cognate from set B. Our results also seem to suggest that non-cognates without cognate synonyms (set B) are better learned than non-cognates with cognate synonyms (set A). This suggests that, at early stages of L2 acquisition, learning a cognate would produce a poorer acquisition of its non-cognate synonym, as compared to a solely learned non-cognate. These results are discussed under the light of different theories and models of bilingual mental lexicon.

The scope of a lucrative career promoted by Google through its video distribution platform YouTube 1 has attracted a large number of users to become content creators. An important aspect of this line of work is the feedback received in the form of comments which show how well the content is being received by the audience. However, volume of comments coupled with spam and limited tools for comment classification makes it virtually impossible for a creator to go through each and every comment and gather constructive feedback. Automatic classification of comments is a challenge even for established classification models, since comments are often of variable lengths riddled with slang, symbols and abbreviations. This is a greater challenge where comments are multilingual as the messages are often rife with the respective vernacular. In this work, we have evaluated top-performing classification models and four different vectorizers, for classifying comments which are a mix of different combinations of English and Malayalam (only English, only Malayalam and Mix of English and Malayalam). The statistical analysis of results indicates that Multinomial Naïve Bayes, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Random Forest and Decision Trees offer similar level of accuracy in comment classification. Further, we have also evaluated 3 multilingual sub-types of the novel NLP language model, BERT and compared its’ performance to the conventional machine learning classification techniques. XLM was the top-performing BERT model with an accuracy of 67.31%. Random Forest with Term Frequency Vectorizer was the best the top-performing model out of all the traditional classification models with an accuracy of 63.59%.

Different factors seemingly account for the emergence of present-day languages in our species. Human self-domestication has been recently invoked as one important force favouring language complexity mostly via a cultural mechanism. As a consequence, evolutionary changes impacting on aggression levels are expected to have fostered this process. Here we hypothesise about a positive effect of dog-human interactions on aggression management and more generally, on our self-domestication, ultimately, contributing to aspects of language evolution. We review evidence of diverse sort (ethological mostly, but also archaeological, genetic, and physiological) supporting a positive feedback loop between dog domestication and human-self domestication that might have favoured the mechanisms promoting structural complexity in human languages.

The speech-to-song illusion is a type of auditory illusion that the repetition of a part of a sentence would change people’s perception tendency from speech-like to song-like. The study aims to examine how pace, emotion, and language tonality affect people’s experience of the speech-to-song illusion. It uses a between-subject (Pace: fast, normal, vs. slow) and within-subject (Emotion: positive, negative, vs. neutral; language tonality: tonal language vs. non-tonal language) design. Sixty Hong Kong college students were randomly assigned to one of the three conditions characterized by pace. They listened to 12 audio stimuli, each with repetitions of a short excerpt, and rated their subjective perception of the presented phrase, whether it sounded like a speech or a song, on a five-point Likert-scale. Paired-sample t-tests and repeated measures ANOVAs were used to analyze the data. The findings reveal that a faster speech pace could strengthen the tendency of the speech-to-song illusion. Neither emotion nor language tonality show a statistically significant influence on the speech-to-song illusion. This study suggests that the perception of sound should be in a continuum and facilitates the understanding of song production in which speech can turn into music by having repetitive phrases and to be played in a relatively fast pace.

The deep neural network - BERT model (Bidirectional Encoder Representations from Transformers) and the stocks cumulative abnormal return is used in this article to analyze the sentiment of financial texts. The proposed approach, unlike those used so far, does not require the creation of dictionaries, takes into account the broad context of words and their meaning in financial texts, eliminates the problem of ambiguity of words in various contexts, does not require manual labelling of data and is free from the subjective assessment of the researcher. The sentiment of financial texts in the meaning presented in this paper is directly related to the market reaction to the information contained in these texts. For texts belonging to one of the two classes (positive or negative) with the highest probability the BERT model gives the results of predictions with a precision level of 62.38% for the positive class and 55% for the negative class. The results at this level can be used in event study, market efficiency research, investment strategy development or support of investment analysts using fundamental analysis.

The high demand for liquefied natural gas (LNG) requires more LNG carriers (LNGCs) to be in operation. During transportation, there is a high risk due to the required extremely low temperatures and the explosive nature of LNG cargo. Moreover, when there is a lack of experience in operating old LNGCs, there is a serious concern regarding operational accidents. A systematic maintenance strategy, especially for LNG cargo containment systems, is crucial for maintaining safe LNG transportation at sea. The purpose of this study is to develop preventive LNG cargo containment system maintenance models by using LNGC dock specifications from LNGCs of various ages. The dock specifications from a conventional LNGC repairing dock were analyzed using natural language processing techniques in order to develop preventive maintenance models of the LNG cargo containment system. From these results, and by considering the ship’s age, it was found that for young LNGCs the priority for repair should focus on checking routine consumable spare parts by tank inspections, whereas for older LNGCs the focus should be on tank condition maintenance rather than on other facilities. These results are expected to be useful in the development of a maintenance strategy of preventive LNG cargo containment systems in maritime LNG transportation.

Estimating Visual Quality of Street Space (VQoSS) is pivotal for urban design, environmental sustainability, civic engagement, etc. Recent advancements, notably in deep learning, have enabled large-scale analysis. However, traditional deep learning approaches are hampered by extensive data annotation requirements and limited adaptability across diverse VQoSS tasks. Multimodal Large Language Models (MLLMs) have recently demonstrated proficiency in various computer vision tasks, positioning them as promising tools for automated VQoSS assessment. In this paper, we pioneer the application of MLLMs to VQoSS change estimation, with our empirical findings affirming their effectiveness. In addition, we introduce Street Quality GPT (SQ-GPT), a model that distills knowledge from the current most powerful but inaccessible (not free) GPT-4, requiring no human efforts. SQ-GPT approaches GPT-4’s performance and is viable for large-scale VQoSS change estimation. In a case study of Nanjin, we showcase the practicality of SQ-GPT and knowledge distillation pipeline. Our work promises to be a valuable asset for future urban studies research.

This article propose a didactic, through games, tool based on information and communication technologies, in order to eliminate possible communication barriers and to promote the inclusion of students with hearing impairment in Physical Education classes. To this end, a dossier of traditional games has been developed. These are structured in turn into objectives, materials, organisation, graphic description and a QR code for each game. These codes are linked to different videos hosted on the YouTube platform, in which the explanation of the games, mentioned above, can be visualised graphically using sign language. The whole creative process is described in the article, as well as possible pedagogical applications of the use of the tools created for this purpose in other educational contexts.

Social media platforms have been entirely an undeniable part of the lifestyle for the past decade. Analyzing the information being shared is a crucial step to understanding human behavior. Social media analysis aims to guarantee a better experience for the user and risen user satisfaction. For deriving any further conclusion, first, it is necessary to know how to compare users. In this paper, a hybrid model has been proposed to measure Twitter profiles’ similarity and quantifies the likeness degree of profiles by calculating features considering users’ behavioral habits. For this, first, the timeline of each profile has been extracted using the official TwitterAPI. Then, in parallel, three aspects of a profile are deliberated. Behavioral ratios are time-series-related information showing the consistency and habits of the user. Dynamic time warping has been utilized to compare the behavioral ratios of two profiles. Next, the audience network is extracted for each user, and for estimating the similarity of two sets, Jaccard similarity is used. Finally, for the Content similarity measurement, the tweets are preprocessed respecting the feature extraction method; TF-IDF and DistilBERT for feature extraction are employed and then compared using the cosine similarity method. Results have shown that TF-IDF has slightly better performance; therefore, the more straightforward solution is selected for the model. Similarity level of different profiles. As in the case study, a Random Forest classification model was trained on almost 20000 users revealed a 97.24% accuracy. This comparison enables us to find duplicate profiles with nearly the same behavior and content.

In today's business world, many companies have realized that consumer feedback evaluations play a crucial part in shaping the company's future activities. The hotel and tourism industries are well-known examples where the user feedback has become crucial. Even though most accommodations want their clients to express their opinions about their services, these reviews are nevertheless carefully reviewed by them. This manual approach is time demanding and error prone, the level of expertise of the individual analyzing the evaluations determines the quality of the manual analysis. This research focuses on the development of a tool-based support system that analyzes text-based customer evaluations and then highlights the maintenance issues identified in the reviews, removing the need to manually evaluate and analyze the customer reviews. The process includes data preparation, sentiment analysis, and a fully trained deep learning model to extract critical insights. Using sentiment analysis techniques after data preprocessing and trained deep learning model, an accuracy of 96\% was achieved, and this paper discusses how this technology helps to meet the needs of accommodation management by completing activities efficiently. This might save management time and helps to save money without losing clients, allowing them to enhance their additional sales.

The COVID-19 pandemic measures have negatively impacted education worldwide via travel restrictions, student visas, and physical attendanc,e among many other fac-tors. As one of the first places to impose strict pandemic measures and one of the last places to lift the measures, Mainland China provided a unique venue to investigate the effect of public health pandemic control policies on tertiary education. Considering the large portion of international students in medical schools and the higher susceptibility to the pandemic measures due to the natural synergy with teaching hospitals, medical schools can be an early forefront indicator of the impact of the pandemic on tertiary education. We surveyed 513 participants international medical students from Wen-zhou Medical University’s school of international studies in 2019 and 2022 about their satisfaction and demographic and cultural adaptation parameters. We found that the pandemic restrictions did not generally impact student satisfaction. Further analyzing the associated parameters, we found teaching satisfaction to be independent of age (P=.159), years in China (P=.896) and Chinese Level (P=.577) in the medical university. Teaching satisfaction is associated with the region of origin (P <0.001), acceptance of local social norms (P <0.001), satisfaction with the core values of Chinese culture (P <0.001), acclimatization to life in China (P <0.001), can easily make Chinese friends (P <0.001) among other factors. The findings of this study provide an understanding of the effects of pandemic measures on tertiary education satisfaction and other factors that can aid in international student satisfaction.

How many different writers authored the huge number of texts attributed to Galen of Pergamum (129~216 AD), medical doctor and philosopher, a giant in the history of medicine? To find out which texts were his and which ones were written by others is known as the “Galenic Question”. We propose a “solution” to it through a multidisciplinary approach based: (a) on historical research and (b) on a mathematical analysis of the Greek texts. The historical approach has considered historical independent sources and anachronisms. The mathematical approach has been based on a mathematical theory concerning deep–language variables, rarely consciously controlled by any author, therefore capable of giving indications on similarity of texts, with little or no bias. The multidisciplinary approach has convinced us that at least three authors wrote the texts attributed to Galen. The first two very likely were real historical persons: (a) a certain Galen living between the end of the I century BC and the second half of the I century AD; (b) the historical Galen of Pergamum (II–III centuries AD) and (c) several unknown authors hiding under the name Galen, but surely living after Galen of Pergamum’s death.

The practice of nurse health coaching (NHC) draws from the art and science of nursing, behavioral sciences, and evidence-based health coaching methods. This secondary analysis of the audio-recorded natural language of participants during NHC sessions of our recent 8-week RCT evaluates improvement over time in cognitive-behavioral outcomes: Change Talk, Resiliency, Self-Efficacy/Independent Agency, Insight & Pattern Recognition, and Building Towards Sustainability. We developed a measurement tool for coding, Indicators of Health Behavior Change (IHBC), that was designed to allow trained health coach experts to assess the presence and frequency of the indicators in the natural language content of participants. We used a two-step method for randomly selecting the 20-minute audio-recorded session that was analyzed at each time point. Fifty-six participants had high-quality audio recordings of the NHC sessions. Twelve participants were placed in the social determinants of health (SDH) group based on the following: low income (<$20,000/year), early-onset hypertension, and social disadvantages. Our analyses significantly improved Change Talk and the other four factors over time. Our factor analyses indicated two distinct factors at each measurement point of the study, demonstrating the stability of the outcome measures over time. Our newly developed measurement tool, IHBC, proved stable in structure over time and sensitive to change. This NHC program shows promise in improving cognitive-behavioral indicators associated with health behavior change in both non-SDH and SDH individuals.

: Multimodal Large Language Models (MLLMs) harness comprehensive knowledge spanning text, images, and audio to adeptly tackle complex problems, including zero-shot in-context learning scenarios. This study explores the ability of MLLMs in visually solving the Traveling Salesman Problem (TSP) and Multiple Traveling Salesman Problem (mTSP) using images that portray point distributions on a two-dimensional plane. We introduce a novel approach employing multiple specialized agents within the MLLM framework, each dedicated to optimizing solutions for these combinatorial challenges. Our experimental investigation includes rigorous evaluations across zero-shot settings and introduces innovative multi-agent zero-shot in-context scenarios. The re-sults demonstrated that both multi-agent models—Multi-Agent 1, which includes the Initializer, Critic, and Scorer agents, and Multi-Agent 2, which comprises only the Initializer and Critic agents—significantly improved solution quality for TSP and mTSP problems. Multi-Agent 1 ex-celled in environments requiring detailed route refinement and evaluation, providing a robust framework for sophisticated optimizations. In contrast, Multi-Agent 2, focusing on iterative re-finements by the Initializer and Critic, proved effective for rapid decision-making scenarios. These experiments yield promising outcomes, showcasing the robust visual reasoning capabilities of MLLMs in addressing diverse combinatorial problems. The findings underscore the potential of MLLMs as powerful tools in computational optimization, offering insights that could inspire further advancements in this promising field.

Generating executable code from natural language instructions using Large Language Models (LLMs) presents challenges such as semantic understanding and handling ambiguous input. This study focuses on the SantaCoder model and explores the impact of in-context learning on code generation using the MBPP and HumanEval datasets for evaluation. Our results demonstrate significant improvements in three key metrics (defined in the paper): correctness@k, similarity@k and pass@k. To address the problem of selecting optimal demonstrations to maximize correctness and pass rates, we investigate two methods: latent concept selection and random selection in this paper. These findings highlight the effectiveness of in-context learning and the critical role of demonstration selection in enhancing the accuracy, efficiency, and versatility of the SantaCoder model in code generation.

The growing usage of Generative AI tools in scientific writing requires a critical examination of their benefits and challenges. This literature review is aimed at comprehensively analyzing current empirical research articles focused on the application of Generative AI in scientific writing. The Google Scholar database was used to search for the literature. The following keywords were used: "Generative AI" and "academic writing", "LLM" (Large Language Models) and "academic writing", "Generative AI" and "Scientific writing", and "ChatGPT" and "Scientific Writing". The search was restricted to articles published between January 1, 2023, and April 30, 2024. 15 articles were selected as appropriate for the study and analyzed. It was found that, thus far, ChatGPT is the most exploited tool in the studies. AI tools such as Bard (Gemini), Bing, Claude2, and Elicit were also tested. The benefits of Generative AI usage in scientific writing were found to be omnipresent. It can aid in the generation of structured abstracts, titles, introductions, literature reviews, and conclusions of a scientific article. Generative AI also makes writing more efficient and time-saving. Its capabilities in improving language and proofreading are well-established. However, the generation of inaccurate content and references by current commercially available LLMs poses a serious problem. The lack of critical thinking and tendency to produce non-original content are significant drawbacks. Generative AI should be employed with human oversight, serving as an assistant rather than a replacement. Transparency in AI usage in scientific writing is essential, along with the necessity for proper legal regulation.

In recent years, e-commerce platforms have replaced conventional marketplaces. People are rapidly adopting internet shopping due to the convenience of making purchases from the comfort of their homes. Online review sites allow customers to share their thoughts on products and services. Customers and businesses are increasingly relying on online reviews to assess and improve the quality of products. Existing literature uses Natural language processing (NLP) to analyze customer reviews for different applications. Due to the growing importance of NLP for online customer reviews, this study attempts to provide a taxonomy of NLP applications based on existing literature. This study also examined emerging methods, data sources, and research challenges by reviewing 154 publications from 2013 to 2023 that explore state-of-the-art approaches for diverse applications. Based on existing research, the taxonomy of applications divides literature into five categories: sentiment analysis, review analysis, customer feedback and satisfaction, user profiling, and marketing and reputation management. It is interesting to note that the majority of existing research relies on Amazon user reviews. Additionally, recent research has encouraged the use of advanced techniques like Bidirectional Encoder Representations from Transformers (BERT), Long Short-Term Memory (LSTM), and ensemble classifiers. The rising number of articles published each year indicates increasing interest of researchers and continued growth. This survey additionally addresses open issues, providing future directions in online customer review analysis.

This study investigates effective strategies for second language education in primary schools, analyzing the efficacy of immersive and interactive methods, digital literacy tools, and mixed-method approaches. The findings reveal significant improvements in language proficiency and student engagement through these methodologies, with immersive and interactive strategies showing substantial benefits in oral proficiency and engagement, digital tools enhancing accessibility and engagement, and mixed-method approaches yielding the highest overall effectiveness. The study underscores the importance of a balanced, flexible approach to language education, integrating traditional and modern methods to cater to diverse learner needs. These strategies not only advance linguistic skills but also contribute to the broader cognitive and emotional development of young learners, emphasizing the critical role of effective language education in preparing students for a globalized world.

Background: Real-world data (RWD) related to the health status and care of cancer patients reflect the ongoing medical practice, and their analysis yields essential real-world evidence. Advanced information technologies are vital for their collection, qualification, and reuse in research projects. Methods: UNICANCER, the French federation of comprehensive cancer centres, has innovated a unique research network : Consore. This potent federated tool enables the analysis of data from millions of cancer patients across eleven French hospitals. Results: Currently operational within eleven French cancer centres, Consore employs natural language processing to structure the therapeutic management data of approximately 1.3 million cancer patients. This data originates from their electronic medical records, encompassing about 65 millions of medical records. Thanks to the structured data, which is harmonized within a common data model, and its federated search tool, Consore can create patient cohorts based on patient or tumor characteristics, and treatment modalities. This ability to derive larger cohorts is particularly attractive when studying rare cancers. Conclusions: Consore serves as a tremendous data mining instrument that propels French cancer centres into the big data era. With its federated technical architecture and unique shared data model, Consore facilitates compliance to regulations and acceleration of cancer research projects.

In the ever-evolving landscape of higher education, the shift to hybrid teaching approaches has introduced novel challenges and opportunities for both educators and students. This qualitative study, grounded in a robust theoretical framework, combines in-depth literature reviews, informal interviews, observations, and thematic analysis to explore the multifaceted dynamics of hybrid language learning within a College of Arts and Sciences. By investigating the experiences of twenty students (referred to as 'S-Part 1' to 'S-Part 20'), the research delves into the core theme of 'Teacher-Student Interaction in Higher Education Institutions' and unpacks nine additional themes: 'Adaptability and Resilience,' 'Flexibility and Autonomy,' 'Connectivity Challenges,' 'Feelings of Isolation,' 'Technology Competence,' 'Personalized Learning,' 'Resource Accessibility,' 'Support Mechanisms,' and 'Positive Learning Experiences.' In this study, these themes encapsulate the diverse experiences and challenges encountered by teachers and college students as they navigate the evolving educational landscape. The insights derived from the study are underpinned by a robust theoretical framework and complemented by existing scholarly literature. As we delve into these themes, it becomes evident that they shed light on not only the intricacies of hybrid language learning but also the broader educational context, offering valuable guidance for educators, institutions, students, and researchers. Based on the ample results, recommendations are presented for school administrators, teachers, students, and future researchers to enhance the quality of hybrid teaching and learning, aligning it with the demands of the post-academic era. Overall, this study contributes to the ongoing dialogue on innovative pedagogical strategies and responsive educational environments, underlining the significance of teacher-student interaction in the new normal of higher education.

Based on the teaching material of "Robotics" course, this paper studied the automatic knowledge graph construction, including knowledge points extraction and knowledge point relation extraction. We proposed a new method of extracting the first-level, second-level, and third-level knowledge points as well as their prerequisite relations of knowledge points in the textbook. For the problem of insufficient knowledge of the pre-trained language model in the specific field, methods such as incremental pre-training and optimization of cost functions are employed to integrate subject knowledge into the pre-trained language model, thus improving its effectiveness. To overcome the problem that the traditional method of relationship extraction can not be applied directly to the extraction of teaching materials, a new scheme for knowledge point relationship extraction based on keyword relationship is proposed. The experimental data from textbooks shows that the F1 score of knowledge point extraction reaches 93%, considerably improved compared to the traditional model. Consequently, the knowledge point entity extraction and relationship extraction methods based on the pre-trained model can effectively extract structured information and facilitate the automatic construction of knowledge graphs.

Social media platforms are increasingly enabling the propagation of content from groups related to drug use, thus posing risks for the wider population and, in particular, individuals who are amenable to drug use and drug addiction. The detection of drug use content on social media platforms is a priority for governments, technology companies, and drug law enforcement organizations. To counter this issue, various techniques have been developed to identify and promptly remove drug use content, while also blocking its creators from network access. In this paper, we introduce a manually annotated Twitter dataset, comprising 156,521 tweets published between 2008 and 2022, specifically compiled for the purpose of drug use detection. The dataset underwent annotation by several group of expert annotators who classified the tweets as either drug use or non-drug use. Exploratory data analysis was conducted to comprehend the dataset's characteristics. Various classification algorithms, including SVM, XGBoost, RF, NB, LSTM, and BERT were employed using the dataset. Among the traditional machine learning models, SVM utilizing term frequency-inverse document frequency features achieved the highest F1-Score (0.9017). However, BERT with textual features concatenated with numerical and categorical features in ensemble method surpassed the performance of traditional models, attaining F1-Score of 0.9112. To facilitate future research and enhance English online drug use classification accuracy, the dataset will be made publicly available.

This qualitative study unveils the intricate interplay between blended learning, language and literature learning, internationalization, and the development of 21st century skills within the realm of higher education. Set against the backdrop of the environment of St. Michael's College in Iligan City, this exploration seeks to unravel the profound significance and transformative implications of these educational dimensions. By delving into the rich perspectives and experiences of 30 college students, this study addresses critical gaps in the literature and sheds light on the potential of these integrated elements. Guided by a robust theoretical framework that amalgamates renowned scholars' insights on blended learning, language acquisition, internationalization, and 21st century skills, the study employs a qualitative research design, employing interviews, observations, and document analysis. The findings illuminate the dynamic nature of blended learning, empowering students with enhanced engagement, flexibility, and accessibility in language and literature education. The incorporation of diverse literary texts and cultural perspectives fosters intercultural competence and global awareness. Moreover, the study underscores the cultivation of critical 21st century skills through immersive learning experiences. Drawing upon the insights gained, the study provides practical recommendations for educators and curriculum designers to harness the potential of blended learning, foster diversity in literary texts, and facilitate the application of 21st century skills. Recognizing the inherent limitations, including the specific context of St. Michael's College and the modest sample size, this study encourages future research to explore broader contexts and diverse participant cohorts. Overall, this illuminating study contributes to the scholarly discourse on integrating blended learning, language and literature learning, internationalization, and 21st century skills in college education. It beckons educators and policymakers to embark on a transformative journey, nurturing an enlightened future where students are equipped with the competencies to navigate the complexities of the 21st century.

Modern language models are designed to generate text so realistic that it could easily be mistaken for human-authored content. Additionally, they can engage in conversations with humans in a manner that appears coherent and reasonable. The epitome of this technological advancement is ChatGPT, a model based on OpenAI's Generative Pretrained Transformer (GPT) language model. With its ability to produce high-quality content in mere seconds, ChatGPT surpasses other chatbots in terms of capabilities, drawing significant interest and excitement from both the business community and academic researchers. This study offers a comprehensive review of current research on ChatGPT, delving into its technological foundation, supportive mechanisms, and findings regarding its benefits across various fields and application areas. We evaluate and discuss the strengths and weaknesses of ChatGPT based on this review and suggest potential avenues for future research.

Numerous goods and services are now offered through online platforms due to the recent growth of online transactions like e-commerce. Users have trouble locating the product that best suits them from the numerous products available in online shopping. Many studies in deep learning-based recommender systems (RSs) have focused on the intricate relationships between the attributes of users and items. Deep learning techniques have used consumer or item-related traits to improve the quality of personalized recommender systems in many areas, such as tourism, news, and e-commerce. Various companies, primarily e-commerce, utilize sentiment analysis to enhance product quality and effectively navigate today's business environment. Customer feedback regarding a product is gathered through sentiment analysis, which uses contextual data to split it into separate polarities. The explosive rise of the e-commerce industry has resulted in a large body of literature on e-commerce from different perspectives. Researchers have made an effort to categorize the recommended future possibilities for e-commerce study as the field has grown. There are several challenges in e-commerce, such as fake reviews, frequency of user reviews, advertisement click fraud, and code-mixing. In this review, we introduce an overview of the preliminary design for e-commerce. Second, the concept of deep learning, e-commerce, and sentiment analysis are discussed. Third, we represent different versions of the commercial dataset. Finally, we explain various difficulties facing RS and future research directions.

With the increasing use of cloud-based services for training and deploying machine learning models, data privacy has become a major concern. This is particularly important for natural language processing (NLP) models, which often process sensitive information such as personal communications and confidential documents. In this study, we propose a method for training NLP models on encrypted text data to mitigate data privacy concerns while maintaining similar performance to models trained on non-encrypted data. We demonstrate our method using two different architectures, namely Doc2Vec+XGBoost and Doc2Vec+LSTM, and evaluate the models on the 20 Newsgroups dataset. Our results indicate that both encrypted and non-encrypted models achieve comparable performance, suggesting that our encryption method is effective in preserving data privacy without sacrificing model accuracy. In order to replicate our experiments, we have provided a Colab notebook at the following address: https://t.ly/lR-TP

The abundance of information in academic articles, reports, and studies can make it challenging for researchers to gain insights from the existing literature. To address this issue, there is a growing demand for tools that can help researchers effectively parse and analyze large volumes of data. One such tool is DataDiscoveryLab, a software system that utilizes computer vision algorithms and NLP techniques to parse academic articles into text and figures, creating three separate databases. These databases allow researchers to quickly identify articles that may be relevant to their research questions, gain a deeper understanding of the research presented, and analyze visual data. The integration of article mining and computer vision in the DataDiscoveryLab software system provides researchers with a powerful tool for navigating the vast amount of scientific literature available today. Yet, as we will discuss in the latter papers these databases’ purpose is to create a bridge between researchers’ data and practically unlimited scientific publications. Yet, in this article, we will discuss how we plan to do that, and our efforts on integrating deep learning modes. After all, unlike already existing AI models, DataDiscoveryLab can be their combination and the first Generative AI in academia that can encompass every part of the natural sciences.

This paper presents ROSGPT, an innovative concept that harnesses the capabilities of large language models (LLMs) to significantly advance human-robot interaction. We develop ROSGPT as a ROS2 package that seamlessly integrates ChatGPT with ROS2-based robotic systems. The core idea is to leverage prompt engineering with LLMs, specifically ChatGPT, utilizing its unique properties such as ability eliciting, chain-of-thought, and instruction tuning. The concept employs ontology development to convert unstructured natural language commands into structured robotic instructions specific to the application context through prompt engineering. We capitalize on LLMs' zero-shots and few-shots learning capabilities by eliciting \textit{structured} robotic commands from \textit{unstructured} human language inputs. To demonstrate the feasibility of this concept, we implemented a proof-of-concept that integrates ChatGPT with ROS2, showcasing the transformation of human language instructions into spatial navigation commands for a ROS2-enabled robot. This versatile concept can be easily adapted to various other robotic missions. ROSGPT serves as a new stride towards Artificial General Intelligence (AGI) and paves the way for the robotics and natural language processing communities to collaborate in creating novel, intuitive human-robot interactions. The open-source implementation of ROSGPT on ROS 2 is available on GitHub.

The ability to identify and rank risk is essential for efficient and effective supervision of financial service firms, such as banks and insurers. Risk ranking ensures limited resources are allocated where they are most needed. Today, automatic risk identification within insurance supervision primarily relies on quantitative metrics based on numerical data (e.g. returns). The purpose of this work is to assess whether Natural Language Processing (NLP) and cognitive networks can achieve similar automated risk ranking and identification by analysing textual data, i.e. NIDT=829 investor transcripts from Bloomberg. To this aim, this work explores and tunes 3 NLP techniques: (1) keyword extraction enhanced by cognitive network analysis; (2) valence/sentiment analysis; and (3) topic modelling. Results highlight that keyword analysis, enriched by term frequency-inverse document frequency scores and semantic framing through cognitive networks, could detect events of relevance for the insurance system like cyber-attacks or the COVID-19 pandemic. Cognitive networks were found to highlight events that related to specific financial transitions: The semantic frame of "climate" grew in size by +538% between 2018 and 2020 and outlined an increased awareness that agents and insurers expressed towards climate change. A lexicon-based sentiment analysis achieved a Pearson’s correlation of ρ=0.16 (p&lt;0.001,N=829) between sentiment levels and daily share prices. Although relatively weak, this finding indicates that insurance jargon is insightful to support risk supervision. Topic modelling is considered less amenable to support supervision, because of a lack of results’ stability and an intrinsic difficulty to interpret risk patterns. We discuss how these automatic methods could complement existing supervisory tools in automated risk ranking.

Electronic health records (EHRs) are becoming a vital source of data for healthcare quality improvement, research, and operations. However, much of the most valuable information contained in EHRs remains buried in unstructured text. The field of clinical text mining has advanced rapidly in recent years, transitioning from rule-based approaches to machine learning and, more recently, deep learning. With new methods come new challenges, however, especially for those new to the field. This review provides an overview of clinical text mining for those who are encountering it for the first time (e.g. physician researchers, operational analytics teams, machine learning scientists from other domains). While not a comprehensive survey, it describes the state of the art, with a particular focus on new tasks and methods developed over the past few years. It also identifies key barriers between these remarkable technical advances and the practical realities of implementation at health systems and in industry.

On review of neuroscience literature extreme capsule considered as a whiter matter tract. Nevertheless it is not clear that extreme capsule itself is a association fiber pathway or is o bottleneck for passing other association fiber. By a systematic search with investigating anatomical position, dissection, connectivity and cognitive role of extreme capsule it can be argued that extreme capsule probably is a bottleneck for passing uncinated fasciculus (UF) and inferior fronto – occipital fasciculus(IFOF), And its different role of language processing is duo to different tract that passing it.

Social media gives researchers an invaluable opportunity to gain insight into different facets of human life.Researchers put a great emphasis on categorizing the socioeconomic status (SES) of individuals to help predict various findings of interest. Forum uses, hashtags and so on are common tools of conversations grouping. On the other hand, crowdsourcing is a concept that involves gathering intelligence to group online user community based on common interest. This paper provides a mechanism to look at writings on social media and group them based on their academic background. We build upon earlier work where we analyzed online forum posts from various geographical regions in the USA and Canada and characterized the readability scores of such users. Specifically, we collected 1000 tweets from the members of the US Senate and computed the Flesch-Kincaid readability score for the Senators. Comparing the Senators’ tweets to the ones from average citizens, we note the following. 1) US Senators’ readability based on their tweets rate is much higher affirming the gap between the academic performance of US Senators and their average citizen, and 2) the immense difference among average citizen’s score compared to those of US Senators is attributed to the wide spectrum of academic attainment.

A novel method for finding linear mappings among word embeddings for several languages, taking as pivot a shared, universal embedding space, is proposed in this paper. Previous approaches learn translation matrices between two specific languages, but this method learn translation matrices between a given language and a shared, universal space. The system was first trained on bilingual, and later on multilingual corpora as well. In the first case two different training data were applied; Dinu’s English-Italian benchmark data, and English-Italian translation pairs extracted from the PanLex database. In the second case only the PanLex database was used. The system performs on English-Italian languages with the best setting significantly better than the baseline system of Mikolov et al. [1], and it provides a comparable performance with the more sophisticated systems of Faruqui and Dyer [2] and Dinu et al. [3]. Exploiting the richness of the PanLex database, the proposed method makes it possible to learn linear mappings among an arbitrary number of languages.

Software engineers from all over the world solve independently a lot of similar problems. In this condition the problem of code or even better architecture reusing becomes an issue of the day. In this paper two phase approach to determining the functional and structural likenesses of software projects is proposed. This approach combines two methods of artificial intelligence: natural language processing techniques with a novel method for comparing software projects based on ontological representation of their architecture automatically obtained from the projects source code. Additionally several similarity metrics are proposed to estimate similarity between projects.

(1) Background: Information overload challenges decision-making in the Industry 4.0 era. While Natural Language Processing (NLP), especially Automatic Text Summarization (ATS), offers solutions, issues with factual accuracy persist. This research bridges cognitive neuroscience and NLP, aiming to improve model interpretability. (2) Methods: This research examined four fact extraction techniques: dependency relation, named entity recognition, part-of-speech tagging, and TF-IDF, in order to explore their correlation with human EEG signals. Representational Similarity Analysis (RSA) was applied to gauge the relationship between language models and brain activity. (3) Results: Named entity recognition showed the highest sensitivity to EEG signals, marking the most significant differentiation between factual and non-factual words with a score of -0.99. The dependency relation followed with -0.90, while part-of-speech tagging and TF-IDF resulted in 0.07 and -0.52, respectively. Deep language models such as GloVe, BERT, and GPT-2 exhibited noticeable influences on RSA scores, highlighting the nuanced interplay between brain activity and these models. (4) Conclusions: Our findings emphasize the crucial role of named entity recognition and dependency relations in fact extraction and demonstrate the independent effects of different models and TOIs on RSA scores. These insights aim to refine algorithms to reflect human text processing better, thereby enhancing ATS models’ factual integrity.

In recent years, the implementation of artificial intelligence (AI) in accounting has grown in many domains, including auditing. AI permits auditors to evaluate large data sets and rapidly identify discrepancies and sequences in audit. This means auditors can review all of a client's transactions via a low time and effort. This entails auditing firms investing heavily in technological infrastructure as well as training their human resources to use cutting-edge AI technologies. Thus, this research sought to investigate the impact of the use of AI techniques by Jordanian external auditors in fraud risk assessment, the moderating effect of auditor size. The descriptive analytical method was used by distributing 280 questionnaires electronically to auditors employed in auditing firms operating in Jordan, The result reveals that AI techniques are extremely beneficial in fraud risk assessment at all levels, and the relationship between the use of AI techniques and the assessment of fraud risk has improved as auditor size has increased.

Text classification is one of the most important task in natural language processing, In this research, we carried out several experimental research on three (3) of the most popular Text classification NLP classifier in Convolutional Neural Network (CNN), Multinomial Naive Bayes (MNB), and Support Vector Machine (SVN). In the presence of enough training data, Deep Learning CNN works best in all parameters for evaluation with 77% accuracy, followed by SVM with accuracy of 76%, and multinomial Bayes with least performance of 69% accuracy. CNN has the best performance in the presence of large enough training dataset because of the presence of filter/ kernels which help to indentify patterns in text data regardless of their position in the sentence. We repeated the training again with just one-third of our data, at this point SVM comes with the best performance, the performance of CNN noticeably drops but still better than Multinomial Naive Bayes, the reason why SVM works best when we reduce the training data was because of its ability to look for a hyper-plane that creates a boundary between different classes of data so as to properly classify them, so we believed that getting the hyper-plane was more efficient when we reduce the dataset, hence reason for the good performance. Multinomial Naive Bayes have the least performance which we attributed to its assumption of independency between the features which sometimes does not hold true. We concluded that availability of data should be an important factor when choosing classifier for Natural Language Processing Text Classification task. CNN should be use in the presence of enough dataset, and SVM should be use when data is not enough. Multinomial Naive Bayes must not be trusted with state of the art NLP task due to its assumption of independency between the features.

A Twi-English parallel corpus is certainly an important resource for Machine Translation of Twi (ISO 639-3), a Low-Resource African Language (LRAL) which is mainly spoken in Ghana and Ivory Coast. Currently large-scale multi-domain Twi-English parallel corpus is still unavailable partly due to the difficulties and the arduous efforts required in its design. In this paper, we present TWIENG: a large-scale multi-domain Twi-English parallel corpus. We crawled the sentences from the web using web crawlers, translated, aligned, tokenized and compiled to create the corpus. We crawled English sentences from Ghanaian indigenous electronic news portals, Ghanaian Parliamentary Hansards, Twi Bible and crowdsourcing via google forms. The sentences were translated by professional translators and linguists, they were then aligned, tokenized and compiled. The corpus was curated using the sketch engine, a corpus manager and analysis software developed by Lexical Computing Limited. The corpus was manually evaluated by Twi professional linguists. The Corpus has 5,419 parallel sentences.

Deep learning is based on matrix computing with a large amount of hidden parameters that is not visible outside the computing module. Deep learning is a non-linear system and a linear approach is not possible. It is natural for people to visualize the algorithm and to follow some hidden parameters. In this paper, we propose a simple graphical programming of a nonlinear system based on drawing the simplest unit, such as a single neuron model. A more complex scheme of a classical neural network is obtained by commands copy-move-place of one neuron. The number of neurons and layers can be chosen arbitrarily. Once the scheme is complete, the implementation code is evaluated with symbolic parameters and nonlinear activation functions. This cannot be done manually. With the symbolic expression of outputs in terms of inputs and symbolic parameters, including symbolic activation pure functions, some other properties can be derived in closed form. This unique original approach can help scientists and developers and design numerical algorithms for machine learning and to understand how deep learning algorithms work.

The deaf-mute and individuals with hearing disabilities who communicate through sign language should not be overlooked or excluded. It is a social responsibility to strive for an inclusive world without inequality. Advances in technology offer various solutions to address the communication gap, one of which is the use of computer-based sign language recognition systems. This project proposes a Malaysian Sign Language recognition model utilizing MobileNetV1, a convolutional neural network-based algorithm, to interpret sign language in real-time settings through a website application using Streamlit. The outcome of the model test shows that it has achieved a recognition rate of 96 percent. Although the proposed model has demonstrated the ability to recognize sign language, it is suggested that further improvement can be achieved by enhancing the quality and diversity of the dataset. The implementation of a more comprehensive dataset would lead to improved performance and increased accuracy of the model. This project underscores the importance of considering and accommodating the needs of the deaf-mute and individuals with hearing disabilities and highlights the potential of technology to bridge communication barriers and achieve a more inclusive society.

The field of program classification, a critical aspect of software engineering, facilitates understanding and categorization of code across various applications, including anomaly detection, and code quality assessment. The advancement of cross-language program classification opens up avenues for efficient code translation among different programming languages, significantly aiding developers in rapid coding and reducing development cycles. Existing research primarily focuses on semantic code analysis, with limited emphasis on cross-linguistic challenges. To address this, we introduce an innovative neural network model, CodeSemanticsNN, which leverages a refined Syntax Structure (SS) approach. This model consists of two integral mechanisms: first, it adopts a novel SS representation that combines sequential and graph-based SS structures, enhancing semantic feature capture. Second, it employs a 'unified vocabulary' strategy to bridge the gap between diverse programming languages, facilitating efficient cross-language classification. Additionally, we have compiled a comprehensive dataset of 20,000 files spanning five programming languages, serving as a benchmark for cross-language classification. Our experiments on this dataset demonstrate that CodeSemanticsNN surpasses existing models in four key metrics: Precision, Recall, F1-score, and Accuracy.

This paper proposes the utilization of large language models as recommendations systems for museums. Since the aforementioned models lack the notion of context, they can’t work with temporal information that is often present in recommendations for cultural environments (e.g. special exhibitions or events). In this respect, the current work aims at enhancing the capabilities of large language models through a fine-tuning process that incorporates contextual information and user instructions. The resulting models are expected to be capable of providing personalized recommendations, aligned with user preferences and desires. More specifically, Generative Pre-trained Transformer 4, a knowledge-based large language model is fine-tuned and turned into a context-ware recommendation system, adapting its suggestions based on user input and specific contextual factors such as location, time of visit, and other relevant parameters. The effectiveness of the proposed approach is evaluated through certain user studies, which ensure an improved user experience and engagement within the museum environment.

Dialogue State Tracking is an essential component in multi-domain dialogue systems, aiming to accurately determine the current dialogue state based on the dialogue history. Existing research has addressed the issue of multiple mappings in dialogues by employing slot self-attention as a data-driven approach. However, learning the relationships between slots from a single sample has limitations and introduces noise. In this paper, we propose an External Slot Relation Memory-based Dialogue State Tracking model (ER-DST). By utilizing an external memory storage, we learn the relationships between slots as a dictionary of multi-domain slot relations. Additionally, we employ a small filter to discard slot information irrelevant to the current dialogue state. Experimental results on the MultiWOZ2.0 and MultiWOZ2.1 benchmarks demonstrate significant improvements while reducing the time complexity to O(n).

In recent years, the rise of advanced artificial intelligence technologies has had a profound impact on many fields, including education and research. One such technology is ChatGPT, a powerful large language model developed by OpenAI. This technology offers exciting opportunities for students and educators, including personalized feedback, increased accessibility, interactive conversations, lesson preparation, evaluation, and new ways to teach complex concepts. However, ChatGPT poses different threats to the traditional education and research system, including the possibility of cheating on online exams, human-like text generation, diminished critical thinking skills, and difficulties in evaluating information generated by ChatGPT. This study explores potential opportunities and threats that ChatGPT poses to overall education from the perspective of students and educators. Furthermore, for programming learning, we explore how ChatGPT helps students improve their programming skills. To demonstrate this, we conducted different coding-related experiments with ChatGPT, including code generation from problem descriptions, pseudocode generation of algorithms from texts, and code correction. We also verified the generated codes with an online judge system to evaluate their accuracy.

Background: This study presents a graph-based and purely structural analysis to detect echo chambers on Twitter. Echo chambers are a concern as they can spread misinformation and reinforce harmful stereotypes and biases in social networks. Methods: The study recorded the German-language Twitter stream over two months, recording about 180.000 accounts and their interactions. The study focuses on retweet interaction patterns in the German-speaking Twitter stream and found that the greedy modularity maximization and HITS metric are the most effective methods for identifying echo chambers. Results: The purely structural detection approach was able to identify an echo chamber (red community) that was focused on a few topics with a triad of Anti-Covid, right-wing populism, and pro-Russian positions (very likely reinforced by Kremlin-orchestrated troll accounts). In contrast, a blue community was much more heterogeneous and showed "normal" communication interaction patterns. Conclusions: The study highlights the effects of echo chambers as they can make political discourse dysfunctional and foster polarization in open societies. The presented results contribute to identifying problematic interaction patterns in social networks often involved in the spread of disinformation by problematic actors. It is important to note that not the content but only the interaction patterns would be used as a decision criterion, thus avoiding problematic content censorship.

“A Picture is worth a thousand words”. Given an image, humans are able to deduce various cause-and-effect captions of past, current, and future events beyond the image. The task of visual commonsense generation aims at generating three cause-and-effect captions (1) what needed to happen before, (2) what is the current intent, and (3) what will happen after for a given image. However, such a task is challenging for machines owing to two limitations: existing approaches (1) directly utilize conventional vision-language transformers to learn relationships between input modalities, and (2) ignore relations among target cause-and-effect captions but consider each caption independently. We propose Cause-and-Effect BART (CE-BART) which is based on (1) Structured Graph Reasoner that captures intra- and inter-modality relationships among visual and textual representations, and (2) Cause-and-Effect Generator that generates cause-and-effect captions by considering the causal relations among inferences. We demonstrate the validity of CE-BART on VisualCOMET and AVSD benchmarks. CE-BART achieves SOTA performances on both benchmarks, while extensive ablation study and qualitative analysis demonstrate the performance gain and improved interpretability.

Background: In the present study, we assessed the feasibility and success outcomes of voice prosthesis (VP) changes when performed by speech-language pathologist (SLP). Methods: Patients treated with total laryngectomy (TL) from January 2020 to December 2020 were prospectively recruited from our medical center. Patients benefited from tracheoesophageal puncture. The VP changes were performed by the senior SLP and the following data were collected for each VP change: date of placement; change or removal; VP type and size; reason for change or removal; and use of a washer for periprosthetic leakage. A patient-reported outcome questionnaire including 6 items was proposed to patients at each VP change (Appendix 1). Items were assessed with a 10-point Likert-scale. Results: Fifty-two VP changes were performed by the senior SLP during the study period. The mean duration of the SLP consultation, including patient history, examination and VP change procedure was 20 min (range: 15-30). The median prosthesis lifetime was 88 days. The main reasons for VP changes were transprosthetic (N=34; 79%) and periprosthetic (N=7; 21%) leakages, respectively. SLP successfully performed all VP changes. He did not change one VP but used a periprosthetic silastic to stop the periprosthetic leakages. In two cases, SLP needed the surgeon examination to discuss about the following indication: implant mucosa inclusion and autologous fat injection. The patient satisfaction was high according to the speed and the quality of care by the SLP. Conclusion: The delegation of VP change from the otolaryngologist-head and neck sur-geon to the speech-language pathologist (SLP) may be done without significant complications. The delegation of VP change procedure to SLP may be interesting in some rural regions with otolaryngologist shortage.

The computer network world is changing and the NetDevOps approach has brought the dynamics of applications and systems into the field of communication infrastructure. Businesses are changing and businesses are faced with difficulties related to the diversity of hardware and software that make up those infrastructures. The "Intent-Based Networking - Concepts and Definitions" document describes the different parts of the ecosystem that could be involved in NetDevOps. The recognize, generate intent, translate and refine features need a new way to implement algorithms. This is where artificial intelligence comes in.

Abstract: Understanding social media networks and group interactions are crucial to the ad-vancement of linguistic and cultural behaviour. This includes the manner in which people ac-cessed advice on health, especially during the global lockdown periods. Some people turned to social media to access information on health where most activities were curtailed with isolation rules, especially for older generations. Facebook public pages, groups and verified profiles, using "senior citizen health", "older generations", and "healthy living" keywords were analysed over a 12-month period to analyse the engagement promoting good mental health. CrowdTangle was used to source English language status updates, photo and video sharing information which resulted in an initial 116,321 posts and 6,462,065 interactions Data analysis and visualisation were used to explore large datasets, including natural language processing for “Message” content discovery, word frequency and correlational analysis and co-word clustering. Preliminary results indicate strong links to healthy aging information shared on social media which showed correla-tions to global daily confirmed case and daily death totals. The results can be used to identify public concerns early on and address mental health issues in the senior generation on Facebook.