An integrated service recommendation approach for service-based system development

With the wide adoption of service-oriented computing and cloud computing, service-based systems (SBSs), a kind of software systems that can offer certain functionalities by leveraging one or more Web services, become increasingly popular. A challenging issue in SBS development is to find suitable services from a variety of available (semantics different) services. Towards this issue, we propose a new service recommendation approach that can integrate diverse information of SBSs and their component services. In this research, SBSs, services, their respective attributes (e.g. content and categories) and SBS-service composition relations are modeled as a heterogeneous information network (HIN); and several semantic similarities between SBSs are measured on a set of meta-paths in the HIN. Particularly, a word embedding technique is used to learn word vectors from the content of SBSs and services, which contribute to better functional similarities between SBSs. Afterwards, the combinational weights of different similarities are optimized using a Bayesian personalized ranking algorithm. Services are finally recommended based on collaborative filtering. We identify two recommendation scenarios with different SBS requirements. By conducting a series of experiments on a real-world dataset crawled from the ProgrammableWeb, we validate the effectiveness of our approach and find out the optimal combinations of SBS similarities for those two scenarios. (C) 2019 Elsevier Ltd. All rights reserved.