Date of Award

Spring 6-4-2025

Document Type

Thesis (Undergraduate)

Department

Computer Science

First Advisor

Andrew Campbell

Second Advisor

Arvind Pillal

Abstract

This research investigates the capability of Vision Language Models (VLMs), specifically ChatGPT‑4o, to interpret and predict psychological outcomes based on visual representations of time series data. Leveraging conversation duration metrics and psychological flourishing scores from the StudentLife dataset, this study rigorously evaluates the predictive accuracy of VLMs using various methods, including zero‑shot on raw data, zero‑shot on graph data, few‑shot learning, qualitative labeling, and chain‑of‑thought reasoning. Despite multiple methodological enhancements, predictive performance remains modest, revealing significant challenges in quantitative interpretation of visualized temporal data by current multimodal models. We demonstrate that standardizing input tokens by using graph images rather than raw numerical sequences reduces token footprint, enables few‑shot contexts, and improves qualitative reasoning, even if quantitative metrics change only marginally. The outcomes emphasize the need for advancements in both visualization methods and model fine‑tuning to bridge the gap between descriptive and predictive capabilities.

Share

COinS