Automating API Documentation with LLMs: A BERTopic Approach
This work addresses the challenge for Android developers by making API resources more accessible and actionable, though it is incremental as it applies existing methods to a new domain.
The paper tackled the problem of lengthy and incomplete official API documentation by automating summarization of informal sources like Stack Overflow posts for Android APIs, using BERTopic to extract topics from 3.6 million posts and extractive summarization to generate concise summaries with code snippets, resulting in improved productivity as shown in a user study with 30 developers.
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 Android 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, showing improved productivity. Integrating formal API knowledge with community-generated content enhances documentation, making API resources more accessible and actionable work.