Automating API Documentation with LLMs: A BERTopic Approach

Naghshzan, AmirHossein

arXiv.org Artificial Intelligence 

Developers rely on API documentation, but official sources are often lengthy, complex, or incomplete. Many turn to community - driven forums like Stack Overflow for practical insights. We propose automating the summarization of informal sources, focusing on An - droid APIs. Using BERTopic, we extracted prevalent topics from 3.6 million Stack Overflow posts and applied extractive summarization techniques to generate concise summaries, including code snippets. A user study with 30 Android developers assessed the summaries for coherence, relevance, informativeness, and satisfaction, show - ing improved productivity. Integrating formal API knowledge with community - generated content enhances documentation, making API resources more accessible and actionable work.