Document Type
Poster
Publication Date
Spring 2025
Abstract
This study uses topic modeling to analyze over 17,000 English-language conversations from the WILDCHAT-FULL dataset, a large-scale collection of human-ChatGPT interactions. By applying Latent Dirichlet Allocation (LDA) across 17 time-based segments spanning one year, the research identifies major themes and temporal shifts in user engagement. Creative writing emerged as the dominant topic category, accounting for nearly 40% of all identified topics. Subcategories such as character development, fight scenes, and sexual content offer further insight into how users creatively engage with ChatGPT. By combining large-scale topic modeling with close qualitative review, this study demonstrates a scalable yet nuanced approach to analyzing the evolving landscape of human-AI communication.
Recommended Citation
Sussman, Hannah, "Understanding Human-AI Interactions: What 17,000 Conversations Reveal About Creativity and ChatGPT" (2025). IPHS 484: Senior Seminar. Paper 38.
https://digital.kenyon.edu/dh_iphs_ss/38
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.