Mining API Usage Scenarios from Stack Overflow

TL;DR

This paper introduces a framework that extracts API usage scenarios from Stack Overflow, linking code examples to APIs, summarizing discussions, and analyzing developer reactions to assess code quality.

Contribution

It presents novel algorithms for automatically linking code snippets to APIs, generating natural language task descriptions, and associating developer reactions, evaluated on three benchmarks.

Findings

Algorithms effectively link code to APIs and summarize discussions.

Developer reactions provide insights into code quality.

Framework enables systematic mining of API usage insights.

Abstract

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.