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.

Creative Commons License

Creative Commons Attribution 4.0 License
This work is licensed under a Creative Commons Attribution 4.0 License.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.