A Collaborative Filtering Algorithm Based on Sentiment Analysis in Review Texts

To improve the performance of collaborative filtering algorithm, a algorithm based on sentiment analysis in review texts (CF_SA) is proposed this paper. First, LDA (Latent Dirichlet Allocation) used to form user topic feature matrix and calculate similarity. Secondly, ALBERT(A Lite Bidirectional Encoder Representation from Transformers) model BiLSTM(Bi-directional Long Short-Term Memory) neural network are mine users' emotional tendencies item texts, rating table, Next, similarity combined obtain final predict user's for item. Finally, experiments were conducted Douban Film Review dataset. Compared with classic recommendation algorithms, results show that has good performance.