Mining ETDs for Trends in Graduate Research.

Our ongoing research project applies computational analysis and text mining techniques to a large corpus of electronic theses and dissertations (ETDs) in order to gain insight into the evolution of graduate research topics. We analyze a dataset made up of over 1.3 million full-text ETDs and their associated metadata, spanning the years 2000 to 2018, accessed via the ProQuest TDM Studio. We employ methods such as co-occurrence graph analysis to visualize trends in the data and draw conclusions by analyzing its evolution. We share the insights gained through text and data mining the ETD corpus, how different topics and disciplines overlap and thus map the interdisciplinarity among them, the evolution of interdisciplinarity in graduate research, and areas of scholarly growth within and across disciplines. This project was supported in part by ProQuest, which provided access to TDM Studio and the ProQuest Dissertations & Theses Global corpus. This project was also made possible in part by the Institute of Museum and Library Services (lg-37-19-0078-19).