A Recommendation Model of Deeply Fusion Rating matrix and Review Text
Meigen Huang, Nan Xiao · 2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA) · 2022
With the development of deep learning technology, some work applies deep learning to recommendation system. In order to further improve the quality of recommendation, we propose a recommendation model of deeply fusion rating matrix and review text. In this paper, the variable convolution neural network is used to process the review text, and the attention mechanism is introduced to extract the representative reviews. The depth neural network is used to process the rating, extract the depth features, and fuse the features to predict the user's rating. In this paper, three real data sets are verified, and the mean square error MSE is used as the evaluation index. The results show that our proposed model can achieve better recommendation effect than multiple baseline models.