Generating Question Titles for Stack Overflow from Mined Code Snippets

TL;DR

This paper presents a deep learning-based method to automatically generate high-quality question titles from code snippets on Stack Overflow, aiming to improve question clarity and answerability.

Contribution

It introduces a novel sequence-to-sequence model with attention, copy, and coverage mechanisms for generating question titles from code snippets across multiple programming languages.

Findings

Outperforms state-of-the-art baselines in automatic metrics

Achieves higher human evaluation scores for question quality

Effective across diverse programming languages

Abstract

Stack Overflow has been heavily used by software developers as a popular way to seek programming-related information from peers via the internet. The Stack Overflow community recommends users to provide the related code snippet when they are creating a question to help others better understand it and offer their help. Previous studies have shown that} a significant number of these questions are of low-quality and not attractive to other potential experts in Stack Overflow. These poorly asked questions are less likely to receive useful answers and hinder the overall knowledge generation and sharing process. Considering one of the reasons for introducing low-quality questions in SO is that many developers may not be able to clarify and summarize the key problems behind their presented code snippets due to their lack of knowledge and terminology related to the problem, and/or their poor writing skills, in this study we propose an approach to assist developers in writing high-quality questions by automatically generating question titles for a code snippet using a deep sequence-to-sequence learning approach. Our approach is fully data-driven and uses an attention mechanism to perform better content selection, a copy mechanism to handle the rare-words problem and a coverage mechanism to eliminate word repetition problem. We evaluate our approach on Stack Overflow datasets over a variety of programming languages (e.g., Python, Java, Javascript, C# and SQL) and our experimental results show that our approach significantly outperforms several state-of-the-art baselines in both automatic and human evaluation. We have released our code and datasets to facilitate other researchers to verify their ideas and inspire the follow-up work.