Recommendation system plays an indispensable role in helping users make decisions in different application scenarios. The issue about how to improve the accuracy of a recommendation system has gained widespread concern in both academic and industry fields. To solve this problem, many models have been proposed, but most of them usually focus on a single perspective. Different from the existing work, we propose a hybrid recommendation method based on the users’ social trust network in this study. The proposed method has several advantages over conventional recommendation solutions. First, it offers a reliable two-step way of determining reference users by employing direct trust between users in the social trust network and setting a similarity threshold. Second, it improves the traditional collaborative filtering (CF) method based on a Pearson Correlation Coefficient (PCC) to reduce extreme values in prediction. Third, it introduces a personalized local social influence (LSI) factor into the improved CF method to further enhance the prediction accuracy. Seventy-one groups of random experiments based on the real dataset Epinions in social networks verify the proposed method. The experimental results demonstrate its feasibility, effectiveness, and accuracy in improving recommendation performance.
Compared to traditional heterogeneous graph (HG) data, Bi-typed Multi-relational Heterogeneous Graph (BMHG) not only have various edge relationships between different types of nodes but also connections among the same type of nodes, which increases modeling complexity. However, existing Heterogeneous Graph Neural Networks (HGNN) primarily focus on HGs with single relationships and are ineffective for BMHGs. These methods often rely on meta-paths to capture node features, which leads to the loss of intermediate node information. To address this, this paper proposes a Semantic Fusion-based Bi-typed Multi-relational Heterogeneous Graph model (SF-BMHG), aimed at solving the challenges of multiple edge relationships and complex semantic information processing among nodes in BMHGs. SF-BMHG first generates new features with intermediate nodes through a feature fusion strategy to avoid the loss of intermediate node information. It then captures semantic information in BMHGs using the new node features and meta-relation paths, integrating features from different semantic paths with a semantic-level attention mechanism. Additionally, it employs relational convolutions to capture relationship features within different types and fuses different relationship features through a relational-level attention mechanism. Ultimately, SF-BMHG combines intra-type relationship features and inter-type semantic features to produce rich feature embeddings. Experimental results on real-world constructed datasets demonstrate that, compared to existing baseline methods, SF-BMHG achieves superior performance across various tasks.