Analyses of faculty citation activity usually focus on counts as a function of author characteristics such as rank, gender, previous citation levels, and other factors influencing productivity and career path. Citation analyses of publications consider aspects such as number of authors, author reputation, author order, length of the title, methodology, and impact factors of the publication. While publication topics or discipline are considered to be important factors, they are more difficult to analyze, and therefore performed less frequently. This paper attempts to do that for the field of urban planning. Urban planning is multi-disciplinary and includes consideration of social, economic, technological, environmental, and political systems that shape human settlement patterns. It has been suspected that some topics are more “popular” and have larger audiences, therefore are cited more often. Using nearly 15,000 urban planning publications, this paper presents an analysis of topics to assess which are cited most frequently. The classification of publications was performed using a Support Vector Machine (SVM), a machine learning (ML) approach to text classification, using citation data from Google Scholar. The citation levels for the resulting categories are analyzed and discussed.