1. A Hybrid Model Based on LFM and BiGRU Toward Research Paper Recommendation
- Author
-
Ziqing Nie, Xu Zhao, Chenkun Meng, Tie Feng, and Hui Kang
- Subjects
Word embedding ,General Computer Science ,Computer science ,Feature vector ,Feature extraction ,02 engineering and technology ,Semantics ,computer.software_genre ,LFM ,Matrix decomposition ,020204 information systems ,0202 electrical engineering, electronic engineering, information engineering ,Recommender systems ,General Materials Science ,BiGRU ,user attention ,Artificial neural network ,business.industry ,Deep learning ,General Engineering ,deep learning ,TK1-9971 ,020201 artificial intelligence & image processing ,Artificial intelligence ,Data mining ,Electrical engineering. Electronics. Nuclear engineering ,business ,computer ,Word (computer architecture) - Abstract
To improve the accuracy of user implicit rating prediction, we combine the traditional latent factor model (LFM) and bidirectional gated recurrent unit neural network (BiGRU) model to propose a hybrid model that deeply mines the latent semantics in the unstructured content of the text and generates a more accurate rating matrix. First, we utilize the user’s historical behavior (favorites records) to build a user rating matrix and decompose the matrix to obtain the latent factor vectors of users and literature. We also apply the BERT model for word embedding of the research papers to obtain the sequence of word vectors. Then, we apply the BiGRU with the user attention mechanism to mine the research paper textual content and to generate the new literature latent feature vectors that are used to replace the original literature latent factor vectors decomposed from the rating matrix. Finally, a new rating matrix is generated to obtain users’ ratings of noninteractive research papers and to generate the recommendation list according to the user latent factor vector. We design experiments on the real datasets and verify that the research paper recommendation model is superior to traditional recommendation models in terms of precision, recall, F1-value, coverage, popularity and diversity.
- Published
- 2020