Four-dimensional trust propagation model for improving the accuracy of recommender systems

Collaborative filtering (CF) is the most popular approach for predicting relevant items in recommender systems. However, basic CF suffers from some serious problems including data sparsity and cold start. Incorporating trust inferences into traditional collaborative filtering is an effective approach to overcoming these problems and obtaining more accurate recommendations. Since the value of direct trust in a user is not always available, trust propagation, i.e., indirect estimation of the trust level, may be helpful in a trust-based recommendation. The effectiveness and accuracy of trust-based recommendation systems may be improved if different parameters are taken into account in trust propagation. In this paper, we introduce a four-dimensional trust propagation model for use in recommendation systems in which social distance, location, time, and context are all taken into account. In the proposed model, firstly using the subjective logic model, a confidence-aware trust propagation procedure is run to estimate the indirect trust values based on social links between users. Then, a compound similarity measure is calculated based on the closeness among ratings in terms of time, location, and context. This similarity measure is used to estimate final trust values among users. Finally, rating estimation is done using the levels of trust as weights. The results of the conducted experiments on well-known datasets demonstrate that the proposed model provides higher effectiveness and accuracy comparing the existing methods. An ablation analysis was conducted to evaluate the contribution of each feature dimension to the proposed model. Also, the complexity of the method was analyzed, which confirms the scalability of the model.