Researching the Research: Applying Machine Learning Techniques to Dissertation Classification

Abstract

This research examines industry-based dissertation research in a doctoral computing program through the lens of machine learning algorithms to determine if natural language processing-based categorization on abstracts alone is adequate for classification. This research categorizes dissertation by both their abstracts and by their full-text using the GraphLab Create library from Apple’s Turi to identify if abstract analysis is an adequate measure of content categorization, which we found was not. We also compare the dissertation categorizations using IBM’s Watson Discovery deep machine learning tool. Our research provides perspectives on the practicality of the manual classification of technical documents; and, it provides insights into the: (1) categories of academic work created by experienced fulltime working professionals in a Computing doctoral program, (2) viability and performance of automated categorization of the abstract analysis against the fulltext dissertation analysis, and (3) natual language processing versus human manual text classification abstraction.