LLMSARec: large language model with semantic alignment for Web service recommendation

Purpose With the continuous increase in Web services, efficient identification of Web services that meet developers’ needs and understanding their relationships remains a challenge. Previous research has improved recommendation effectiveness by using correlations between Web services through graph neural networks (GNNs), while it has not fully leveraged service descriptions, limiting the depth and diversity of learning. To this end, a Web services recommendation method called LLMSARec, based on Large Language Model and semantic alignment, is proposed. This study aims to extract potential semantic information from services and learn deeper relationships between services. Design/methodology/approach This method consists of two core modules: profile generation and maximizing mutual information. The profile generation module uses LLM to analyze the descriptions of services, infer and construct service profiles. Concurrently, it uses LLM as text encoders to encode inferred service profiles for enhanced service representation learning. The maximizing mutual information model aims to align the semantic features of the services text inferred by LLM with structural semantic features of the services captured by GNNs, thus achieving a more comprehensive representation of services. The aligned representation serves as an input for the model to identify services with superior matching accuracy, thereby enhancing the service recommendation capability. Findings Experimental comparisons and analyses were conducted on the Programmable Web platform data set, and the results demonstrated that the effectiveness of Web service recommendations can be significantly improved by using LLMSARec. Originality/value In this study, the authors propose a Web service recommendation approach based on Large Language Model and semantic alignment. By extracting latent semantic information from services and effectively aligning semantic features with structural features, new representations can be generated to significantly enhance recommendation accuracy.