Generating Question Titles for Stack Overflow from Mined Code Snippets

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.

SOTitle: A Transformer-based Post Title Generation Approach for Stack Overflow

“…Until now, millions of developers use Stack Overflow to search for high-quality answers for their programming problems. Moreover, Stack Overflow becomes a knowledge base for developers to learn programming skills by browsing high-quality posts [1] [2] [3] [4].…”

“…These low-quality question posts not only fail to get effective help, but also hinder the process of knowledge generation [6] [7]. To solve this problem, previous studies have been conducted on the quality prediction of the question posts [1], [8]- [13]. For example, Correa and Sureka [10] surveyed the closed problems in Stack Overflow and found that high-quality problems should contain enough code for others to reproduce the problem.…”

“…To our best knowledge, Gao et al [1] were the first to automatically generate a post title according to a specific code snippet. However, they ignored the valuable information in the corresponding problem description.…”

“…The main ideas of our proposed approach SOTitle have three aspects. (1) We model the multi-modal input by concatenating the code snippet and the problem description together and follows the Transformer structure. (2) We formalize question post title generation for each programming language as separate but related tasks.…”

Generating Question Titles for Stack Overflow from Mined Code Snippets

“…• We collected more than 1M ⟨code snippet, question⟩ pairs from Stack Overflow, which covers a variety of programming languages (e.g., Python, Java, Javascript, C# and SQL). We have released our code 6 and datasets [17] to facilitate other researchers to repeat our work and verify their ideas. We also implemented a web service tool, named Code2Que to facilitate developers and inspire the follow-up work.…”