Web Service Recommendation Based on Word Embedding and Node Embedding

作者：Bo Jiang, Hang Li, Junchen Yang, Yanbin Qin, Liuhai Wang, Weifeng Pan · 发表于：Mobile Information Systems · 年份：2022 · DOI：10.1155/2022/5106001 · 被引用次数：7 · 研究领域：Recommender Systems and Techniques、Web Data Mining and Analysis、Service-Oriented Architecture and Web Services

Thanks to the rapid development of service-oriented computing (SOC) technologies, the number of Web services, such as Web API, is increasing rapidly. However, this brings some difficulties for mashup (a kind of Web API composition) developers to choose appropriate Web Services to build their projects. Finding required Web APIs from a large number of candidates and recommending them to developers has become a vital issue in mashup development. The traditional collaborative filtering algorithm has the problems of cold start and sparse data. In order to solve the deficiency of the collaborative filtering algorithm, we propose an improved hybrid method that combines the two kinds of information to generate word embedding and node embedding, avoiding the cold start problem and data sparsity problem. Experiments on real-world data sets show that our proposed approach is better than five state-of-the-art approaches, which verifies the effectiveness of our approach.