Temporal-Guided Knowledge Graph-Enhanced Graph Convolutional Network for Personalized Movie Recommendation Systems

Abstract

Traditional movie recommendation systems are increasingly falling short in the contemporary landscape of abundant information and evolving user behaviors. This study introduced the temporal knowledge graph recommender system (TKGRS), a ground-breaking algorithm that addresses the limitations of existing models. TKGRS uniquely integrates graph convolutional networks (GCNs), matrix factorization, and temporal decay factors to offer a robust and dynamic recommendation mechanism. The algorithm’s architecture comprises an initial embedding layer for identifying the user and item, followed by a GCN layer for a nuanced understanding of the relationships and fully connected layers for prediction. A temporal decay factor is also used to give weightage to recent user–item interactions. Empirical validation using the MovieLens 100K, 1M, and Douban datasets showed that TKGRS outperformed the state-of-the-art models according to the evaluation metrics, i.e., RMSE and MAE. This innovative approach sets a new standard in movie recommendation systems and opens avenues for future research in advanced graph algorithms and machine learning techniques.

Semantic-Enhanced Variational Graph Autoencoder for Movie Recommendation: An Innovative Approach Integrating Plot Summary Information and Contrastive Learning Strategy

“…First, while we utilized plot summaries as additional movie information in this study, other sources of information such as movie genres, director, actors, and user demographics could be integrated to further enhance the system's performance. Of particular note, our model can also attempt to incorporate users' dynamic temporal information like in [5]. Second, the proposed model could be extended to other types of recommendation systems, such as music, books, or products, demonstrating its versatility.…”

“…For example, some researchers have approached recommendation as a sequential prediction task by considering the temporal dynamics of users' behaviors [7,31]. Chen and Huang [5] further proposed a model that integrates this idea with traditional methods, resulting in improved performance. This perspective allows us to classify recommender systems into static models and dynamic models based on whether they incorporate dynamic information.…”