A More Accurate Model for Finding Tutorial Segments Explaining APIs
This addresses a practical issue for developers needing to learn unfamiliar APIs from tutorials, though it is incremental as it builds on existing models with new features.
The paper tackles the problem of finding tutorial segments that explain specific APIs, which are scattered across tutorials, by proposing a new model that combines domain-specific features, co-occurrence APIs, knowledge-based API extensions, and Word2Vec. The model achieves up to 90% accuracy in finding relevant fragments and improves the state-of-the-art by up to 30% in F-measure.
Developers prefer to utilize third-party libraries when they implement some functionalities and Application Programming Interfaces (APIs) are frequently used by them. Facing an unfamiliar API, developers tend to consult tutorials as learning resources. Unfortunately, the segments explaining a specific API scatter across tutorials. Hence, it remains a challenging issue to find the relevant segments. In this study, we propose a more accurate model to find the exact tutorial fragments explaining APIs. This new model consists of a text classifier with domain specific features. More specifically, we discover two important indicators to complement traditional text based features, namely co-occurrence APIs and knowledge based API extensions. In addition, we incorporate Word2Vec, a semantic similarity metric to enhance the new model. Extensive experiments over two publicly available tutorial datasets show that our new model could find up to 90% fragments explaining APIs and improve the state-of-the-art model by up to 30% in terms of F-measure.