Mining API Usage Scenarios from Stack Overflow
This work addresses the need for automated mining of API usage information for software developers, but it is incremental as it builds on existing methods for code analysis and summarization.
The authors tackled the problem of extracting API usage scenarios from Stack Overflow by developing a framework that links code examples to APIs, generates task descriptions, and associates developer reactions, achieving evaluation on three benchmarks.
We propose a framework to mine API usage scenarios from Stack Overflow. Each task consists of a code example, the task description, and the reactions of developers towards the code example. First, we present an algorithm to automatically link a code example in a forum post to an API mentioned in the textual contents of the forum post. Second, we generate a natural language description of the task by summarizing the discussions around the code example. Third, we automatically associate developers reactions (i.e., positive and negative opinions) towards the code example to offer information about code quality. We evaluate the algorithms using three benchmarks.