Regular Equivalence

This study explores using regular equivalence in trust networks to improve Collaborative Filtering recommendations, particularly for cold-start users. While traditional CF suffers from data sparsity when users rate few items, incorporating trust relationships (explicit or implicit) can enhance recommendations. The research applies an iterative regular equivalence calculation to generate similarity matrices for neighbor selection, examining how both strong and weak network ties affect recommendation quality. Evaluations on Epinions data demonstrate that incorporating weak ties alongside strong ties significantly improves recommendation accuracy for cold-start users in trust-based recommender systems.

This study uses regular equivalence in trust networks to improve recommendations for cold-start users in Collaborative Filtering systems. By applying this network science measure to user trust relationships, the researchers create a similarity matrix that helps select better user neighbors for recommendation purposes. Testing on the Epinions dataset shows their approach outperforms related methods in recommendation accuracy for new users with few ratings.