Date of Award
M.S. in Engineering Science
Computer and Information Science
Among the myriad of mental conditions permeating through society, psychopathy is perhaps the most elusive to diagnose and treat. With the advent of natural language processing and machine learning, however, we have ushered in a new age of technology that provides a fresh toolkit for analyzing text and context. Because text remains the medium of choice for most personal and professional interactions, it may be possible to use textual samples from psychopaths as a means for understanding and ultimately classifying similar individuals based on the content of their language usage. This paper aims to investigate natural language processing and supervised machine learning methods for detecting and classifying psychopaths based on text. First, I investigate psychopathic texts using natural language processing to tease out major trends that appear in the classical psychological literature. I look at ways to meaningfully visualizing important features within the corpus and examine procedures for statistically comparing the use of function words of psychopaths versus non-psychopaths. Second, I use a “bag of words” approach to investigate the effectiveness of unary-classification and binary-classification methods for determining whether text shows psychopathic indicators. Lastly, I apply standard optimization techniques to tune hyperparameters to yield the best results, while also using a random forest approach to identify and select the most meaningful features. Ultimately, the aim of this research is to validate or disqualify traditional vector-space models on a corpus whose authors consistently try to hide in plain sight.
Henning, Andrew Stephen, "Machine Learning And Natural Language Methods For Detecting Psychopathy In Textual Data" (2017). Electronic Theses and Dissertations. 446.
Emphasis: Computer Science