What Characteristics Make ChatGPT Effective for Software Issue Resolution? An Empirical Study of Task, Project, and Conversational Signals in GitHub Issues

TL;DR

This study analyzes 686 GitHub developer-ChatGPT conversations to identify characteristics that make LLM interactions effective for software issue resolution, highlighting factors like task type, project size, and conversation quality.

Contribution

It provides an empirical analysis of what makes ChatGPT conversations helpful in resolving software issues, offering insights for improving developer tools and LLM fine-tuning.

Findings

ChatGPT is most effective for code generation and API recommendations.

Helpful conversations are shorter, more readable, and semantically aligned.

Larger projects and experienced developers benefit more from ChatGPT.

Abstract

Conversational large-language models are extensively used for issue resolution tasks. However, not all developer-LLM conversations are useful for effective issue resolution. In this paper, we analyze 686 developer-ChatGPT conversations shared within GitHub issue threads to identify characteristics that make these conversations effective for issue resolution. First, we analyze the conversations and their corresponding issues to distinguish helpful from unhelpful conversations. We begin by categorizing the types of tasks developers seek help with to better understand the scenarios in which ChatGPT is most effective. Next, we examine a wide range of conversational, project, and issue-related metrics to uncover factors associated with helpful conversations. Finally, we identify common deficiencies in unhelpful ChatGPT responses to highlight areas that could inform the design of more effective developer-facing tools. We found that only 62% of the ChatGPT conversations were helpful for successful issue resolution. ChatGPT is most effective for code generation and tools/libraries/APIs recommendations, but struggles with code explanations. Helpful conversations tend to be shorter, more readable, and exhibit stronger semantic and linguistic alignment. Larger, more popular projects and more experienced developers benefit more from ChatGPT. At the issue level, ChatGPT performs best on simpler problems with limited developer activity and faster resolution, typically well-scoped tasks like compilation errors. The most common deficiencies in unhelpful ChatGPT responses include incorrect information and lack of comprehensiveness. Our findings have wide implications including guiding developers on effective interaction strategies for issue resolution, informing the development of tools or frameworks to support optimal prompt design, and providing insights on fine-tuning LLMs for issue resolution tasks.