New hybrid semantic-based collaborative filtering recommender systems

The recommender system (RS) improves the users’ experience when searching for and buying items by providing recommendations. This paper presents a new hybrid RS called SemCF. SemCF integrates the item’s semantic information and the historical rating data to generate the recommendations. The semantic information is used to determine the users with the same interests, while rating data is used to estimate the similarity between users in terms of satisfaction level. SemCF produces a unified list of neighbors based on these similarities and uses it in the prediction step. The proposed method is evaluated on two benchmark datasets. The experimental results show its superiority compared to the results of alternative techniques and the ability of SemCF to mitigate cold-start and sparsity. © 2022, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management.