RASOP: An API Recommendation Method Based on Word Embedding Technology

Abstract

Users’ demand for the function of the software is increasingly affluent, and the scale of software is getting larger and larger. The structure of software presents the characteristics of complexity. In the process of software development, developers are likely to face a lot of difficulties, so they need to query the appropriate APIs. However, finding the right APIs can be time-consuming and laborious. It’s especially difficult for developers who don’t have much programming experience. In this paper, to solve the problems developers may face in the actual development process and improve the development efficiency, we propose RASOP (Recommendation APIs by Stack Overflow posts and Java Packages), an API recommendation approach leveraging word embedding technique and the information crawling from Stack Overflow posts and Java core packages, to recommend appropriate APIs for developers. Furthermore, RASOP also provides developers with label words, similar questions and relevant code. To evaluate the effectiveness of RASOP, we decided to analyze our system by simulating an instance. By testing a problem encountered during development, the API and tags and other recommendations from the RASOP output can indeed solve our problem. RASOP shows great results not only in the effect of API recommendation but also in the content of practicability.