Abstract
With the increasing prosperity of web service-sharing platforms, more and more software developers are integrating and reusing Web services when developing applications. This approach not only meets the needs of developers but also is cost-effective and widely used in the field of software development. Usually, software developers can browse, evaluate, and select corresponding Web services from a web service-sharing platform to create various applications with rich functionality. However, a large number of candidate Web services have placed a heavy burden on the selection decisions of software developers. Existing web service recommendation systems often face two challenges. Firstly, developers discover services by inputting development requirements, but the user's input is arbitrary and can not fully reflect the user's intention. Secondly, the application service interaction record is too sparse, reaching 99.9%, making it particularly difficult to extract services that meet the requirements. To address the above challenges, in this paper, we propose a service recommendation method based on text and interaction views (SRTI). Firstly, SRTI employs graph neural network algorithms to deeply mine the historical records, extract the features of applications and services, and calculate their preferences. Secondly, SRTI uses Transformer to analysis develop requirements and uses fully connected neural networks to deeply mine the matching degree between candidate services and development requirements. Finally, we integrate the above two to obtain the final service list. Extensive experiments on real-world datasets have shown that SRTI outperforms several state-of-the-art methods in service recommendation.