Social recommendation often incorporates trusted social links with user-item interactions to enhance rating prediction. Although methods that aggregate explicit social links have shown promising prospects, they are often constrained by the absence of explicit social data and the assumption of homogeneity, thus overlooking variations in social influence and consistency. These limitations hinder semantic expression and recommendation performance. Therefore, we propose a novel framework for social recommendation. First, we design a bipartite network embedding scheme, which learns vertex representations in the embedding space by modeling 1st-order explicit relations and higher-order implicit relations between vertices. Then, the similarity of the embedding vectors is used to extract top-k semantically consistent friends for each user. Next, we design an algorithm to assign a specific influence value to each user. Finally, we combine the top-k friends of the user and their influence values into an ensemble and add it as a regularization term to the rating prediction process of the user to correct the bias. Experiments on three real benchmark datasets show significant improvements in EISF over state-of-the-art methods.

With the increasing number of Web Services, providing accurate and efficient Web APIs to meet the growing demands of developers for Mashups has become a significant challenge. Most existing methods may have not explicitly considered the deep semantic relationships between Web APIs and Mashups, leading to poor recommendation accuracy. In addition to the accuracy of recommendation results, diversity is also considered a key factor in broadening user perspectives and enhancing user satisfaction. However, most current methods have failed to simultaneously explore the assistance of knowledge graphs in accuracy and diversity. To address this problem, this paper proposes a deep knowledge and diversity-awarded Web API recommendation approach (named APIRec). Firstly, We utilize the Mashup-API collaborative invocation pattern and service category attributes to construct a streamlined knowledge graph. Secondly, in this hybrid Mashup-API structure, high-order relations between entities are explicitly implemented in the knowledge graph using an end-to-end approach to uncover hidden relationships among entities. Subsequently, attention mechanisms are employed to model and measure the importance of neighbors. Finally, to enhance the diversity of recommendation results, Maximal Marginal Relevance (MMR) is utilized to measure the accuracy and diversity of the recommended results simultaneously. To verify the effectiveness of APIRec, we conduct extensive experiments on real-world datasets collected from ProgrammableWeb.com. The experimental results show that APIRec outperforms other state-of-the-art approaches by \({\textbf {2.62}}\%\), \({\textbf {4.20}}\%\), and \({\textbf {22.69}}\%\) in terms of mean precision (MP), mean recall (MR), and mean inter-list diversity (MILD), respectively.