Reproduce “TigerGPT: A New AI Chatbot for Adaptive Campus Climate Surveys” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jinwen Tang, Songxi Chen, Yi Shang
Researchers at the University of Missouri's Electrical Engineering and Computer Science Department developed TigerGPT, an AI-powered adaptive chatbot designed to enhance campus climate assessment by offering a more personalized and engaging survey experience than traditional methods. A pilot study with undergraduate students found approximately 81% of participants were satisfied with TigerGPT, with nearly half preferring its conversational approach.
Key insights
- Large Language Models (LLMs) enable adaptive, empathetic conversational surveys, moving beyond static questionnaires.
- Personalized, user-driven topic selection and empathetic communication contribute to higher user engagement and satisfaction in survey contexts.
- A mixed-methods pilot study, combining quantitative metrics and qualitative feedback, effectively validates the benefits and identifies areas for improvement in AI-powered survey systems.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.