Debugging with the Crowd: a Debug Recommendation System based on Stackoverflow

摘要

Debugging is a resource-consuming activity of software development. Some bugs are deeply rooted in the domain logic but others are independent of the specificity of the application being debugged. The latter are "crowd-bugs": unexpected and incorrect output or behavior resulting from a common and intuitive usage of an API. On the contrary, project-specific bugs are related to the misunderstanding or incorrect implementation of domain concepts or logics. We propose a debugging approach for crowd bugs, that is based on matching the piece of code being debugged against related pieces of code on a Q&A website (Stackoverflow). Based on the empirical study of Stackoverflow's data, we show that this approach can help developers to fix crowd bugs.