Abstract
The Collaborative Filtering (CF) algorithm based on trust has been the main method used to solve the cold start problem in Recommendation Systems (RSs) for the past few years. Nevertheless, the current trust-based CF algorithm ignores the implicit influence contained in the ratings and trust data. In this paper, we propose a new rating prediction model named the Rating-Trust-based Recommendation Model (RTRM) to explore the influence of internal factors among the users. The proposed user internal factors include the user reliability and popularity. The internal factors derived from the explicit behavior data (ratings and trust), which can help us understand the user better and model the user more accurately. In addition, we incorporate the proposed internal factors into the Singular Value Decomposition Plus Plus (SVD + +) model to perform the rating prediction task. Experimental studies on two common datasets show that utilizing ratings and trust data simultaneously to mine the factors that influence the relationships among different users can improve the accuracy of rating prediction and effectively relieve the cold start problem.
Highlights
Two internal factors that affect the relationship between different users, namely, user reliability and popularity
Relative to the second-best performance, we show the improvement of our model: (1) The Root Mean Squared Error (RMSE) index of the Rating-Trust-based Recommendation Model (RTRM) improved by 2.441–2.661%, and the Mean Absolute Error (MAE) index improved by 1.689–2.740% in terms of the overall performance
The user internal factors are integrated into a Matrix Factorization (MF) model to improve the accuracy of rating predictions and alleviate the cold start problem
Summary
Two internal factors that affect the relationship between different users, namely, user reliability and popularity. (a) We propose the RTRM that incorporates the users’ internal factors into Matrix Factorization (MF) to improve the accuracy of rating prediction and alleviate the cold start problem. (b) We propose using user reliability and popularity as user internal factors on social impact. User reliability extracted from the user rating represents that the larger the span and the number of his or her ratings, the higher his or her reliability, and the greater their influence on the others. (c) We conduct experimental studies on two datasets, and the experimental results supported the effectiveness of our model in improving the accuracy of rating prediction and alleviating the cold start problem. The factors include: the Potential Vector Dimension K of Users and Items, the Factors Between Users, the Density of Factor Matrix Cu,v and the Training Data Volume
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
