Reinforce Implicit Feedback Recommender Algorithm Integrating Sentiment Analysis
WANG Yuhao
DING Yongmei
Abstract：Recommender systems usually make personalized recommendations based on the interaction data between users and items.The matrix factorization recommender system is to extract the features of users and items to calculate the scores between user items for recommendation ranking.Based on matrix factorization recommender method and deep structured semantic model,this paper constructs a pair of multi-layer perceptron deep neural networks,proposes a deep matrix factorization recommendation model,and designs a strong implicit feedback recommendation algorithm with sentiment analysis.Sentiment features strengthen ex-plicit information,optimize similarity calculation method in model training,and a new loss function to strengthen the implicit feed-back of the model.Compared with other recommendation algorithms,the effectiveness and superiority of the model in the recommen-dation task are proved.
Keywords：recommender systemdeep matrix factorizationsentiment analysisimplicit feedback
Publication Date：2025-06-20
Online Publishing Date：2025-09-23(First online date of this platform, not the publication date of the document)
Pages：5( 1619-1623 )