Date of Graduation
5-2025
Document Type
Thesis
Degree Name
Bachelor of Science in Computer Science
Degree Level
Undergraduate
Department
Computer Science and Computer Engineering
Advisor/Mentor
Gauch, Susan
Committee Member
Wu, Xintao
Second Committee Member
Nakarmi, Ukash
Abstract
The usage of personality as a method of behavioral prediction and outcomes of success has grown considerably over the last few decades. This project explores predicting user personality profiles via the Big Five personality index through the integration of advanced natural language processing techniques as well as neural networks. Using a dataset provided by Dr. James W. Pennebaker, participants analyze an image—formally referred to as a thematic apperception test—and write a thorough paragraph describing the details. This free-form text, along with their personality test results, is captured in a structured dataset. Many deep-learning and machine learning models have been used in the field of psycholinguistics before, but the usage of the Big Five personality model has been relatively scarce, despite it having the highest validity and reliability amongst modern personality indexes. The proposed model extracts personality using word embeddings while incorporating sentiment concentration, typo density, and other linguistic features to capture meaningful insights from participant responses. These features enable the neural network to identify complex linguistic patterns linked to personality traits, presenting a novel approach that leverages many advancements made in the fields of language analysis, psycholinguistics, and modern applications of machine learning. The model’s performance is evaluated by measuring the Mean Squared Error (MSE) between the predicted Big Five traits and the actual traits obtained from the user’s given quiz results. While there is improvement to be made in expanding the scope and accuracy of the model, this project contributes toward advancing accurate computational approaches to personality assessment in the field of computer science.
Keywords
NLP; BFI; TAT; computational; psychology; BERT
Citation
Jones, B. (2025). Usage of Natural Language Processing and Deep-Learning Techniques on Thematic Apperception Tests to Predict Big Five Personality Traits. Electrical Engineering and Computer Science Undergraduate Honors Theses Retrieved from https://scholarworks.uark.edu/elcsuht/3
Included in
Artificial Intelligence and Robotics Commons, Other Computer Sciences Commons, Personality and Social Contexts Commons, Psycholinguistics and Neurolinguistics Commons
