Multimodal Behavioral Patterns Analysis with Eye-Tracking and LLM-Based Reasoning
Guo, Dongyang, Abdrabou, Yasmeen, Thaqi, Enkeleda, Kasneci, Enkelejda
–arXiv.org Artificial Intelligence
Eye-tracking data reveals valuable insights into users' cognitive states but is difficult to analyze due to its structured, non-linguistic nature. While large language models (LLMs) excel at reasoning over text, they struggle with temporal and numerical data. This paper presents a multimodal human-AI collaborative framework designed to enhance cognitive pattern extraction from eye-tracking signals. The framework includes: (1) a multi-stage pipeline using horizontal and vertical segmentation alongside LLM reasoning to uncover latent gaze patterns; (2) an Expert-Model Co-Scoring Module that integrates expert judgment with LLM output to generate trust scores for behavioral interpretations; and (3) a hybrid anomaly detection module combining LSTM-based temporal modeling with LLM-driven semantic analysis. Our results across several LLMs and prompt strategies show improvements in consistency, interpretability, and performance, with up to 50% accuracy in difficulty prediction tasks. This approach offers a scalable, interpretable solution for cognitive modeling and has broad potential in adaptive learning, human-computer interaction, and educational analytics.
arXiv.org Artificial Intelligence
Jul-25-2025
- Country:
- Asia
- China > Guangxi Province
- Nanning (0.04)
- Middle East > Israel (0.04)
- Myanmar > Tanintharyi Region
- Dawei (0.04)
- China > Guangxi Province
- Europe > Germany
- Bavaria > Upper Bavaria > Munich (0.77)
- North America > United States
- New York > New York County > New York City (0.04)
- Oceania > Australia
- Australian Capital Territory > Canberra (0.05)
- Asia
- Genre:
- Instructional Material (1.00)
- Research Report > New Finding (1.00)
- Industry:
- Education
- Educational Setting > Online (0.67)
- Educational Technology (0.68)
- Health & Medicine > Therapeutic Area
- Neurology (0.68)
- Information Technology > Security & Privacy (1.00)
- Education
- Technology: