Author ORCID Identifier

Date of Award

Spring 5-31-2023

Document Type

Thesis (Undergraduate)


Computer Science

First Advisor

Soroush Vosoughi


Chronic pain is a widespread problem that significantly impacts quality of life. Overprescription and abuse of pain medication continues to be a major public health issue and can further burden patients due to a fragmented health care system. Previous research has suggested a possible psychological basis to pain and the potential for safer, non-pharmacological alternatives for pain relief. This project leverages language models to study chronic pain development and relief through psychological treatments, which will be assessed through responses to post-treatment interviews. A transformer-based natural language processing model is employed to identify connections between language expressions and pain on a dataset of back pain questionnaires. The features of the text are further analyzed through SHAP analysis to explain the model’s predictions. From the results, we discovered no significant correlation between the predicted and observed values of the general regression and classification models. We also found a slightly stronger correlation for the regression model for the placebo treatment, and no transfer in performance from generated data-trained regression and classification models. Further study of this topic could lead to more reliable prediction of pain relief by linguistic features.