On the Taxonomy of Developers’ Discussion Topics with ChatGPT

Large language models (LLMs) like ChatGPT can generate text for various prompts. With exceptional reasoning capabilities, ChatGPT (particularly the GPT-4 model) has achieved widespread adoption across many tasks - from creative writing to domain-specific inquiries, code generation, and more. This research analyzed the DevGPT dataset to determine common topics posed by developers interacting with ChatGPT. The DevGPT dataset comprises ChatGPT interactions from GitHub issues, pull requests and discussions. By employing a mixed-methods approach combining unsupervised semantic modeling and expert qualitative analysis we categorize the topics developers discuss when interacting with ChatGPT.Our approach reveals 17 topics within seven categories, with over 25% of prompts focused on advanced programming guidance. Additional areas of significant query volume include DevOps workflows, SQL, databases, and specialized domains, such as localization, streaming media, and image processing. This research effectively illuminates core topics and dependencies that motivate developers to leverage ChatGPT. The taxonomy classification further clarifies critical areas to better customize AI tools for aligning with workflows and needs within software engineering contexts.CCS CONCEPTS• Software and its engineering → Programming teams.