Towards automatically generating summary comments for Java methods

TLDR

Good comments aid program comprehension and maintenance, yet most software projects lack adequate comments. The study proposes automatically generating descriptive summary comments for Java methods to address the scarcity and obsolescence of human‑written comments. The generator analyzes a method’s signature and body to identify key content and produces natural‑language summary comments. Programmers judged the generated summaries to be accurate, comprehensive, and concise.

Abstract

Studies have shown that good comments can help programmers quickly understand what a method does, aiding program comprehension and software maintenance. Unfortunately, few software projects adequately comment the code. One way to overcome the lack of human-written summary comments, and guard against obsolete comments, is to automatically generate them. In this paper, we present a novel technique to automatically generate descriptive summary comments for Java methods. Given the signature and body of a method, our automatic comment generator identifies the content for the summary and generates natural language text that summarizes the method's overall actions. According to programmers who judged our generated comments, the summaries are accurate, do not miss important content, and are reasonably concise.