Wentao Wang
ABSTRACT
In recent years, recommendation models have been widely used in various fields, but the existing recommendation models mostly focus on user historical behavior learning or the analysis of the internal relationship of items, and it is difficult to take into account the effective extraction of deep-level user features and item features. In view of this, this paper studies and proposes a GRU and CNN combined recommendation model with Self-Attention mechanism. The model uses GRU and Self-Attention mechanisms to extract user features, combines with CNN to capture the local relevant features of the item. Then through the full connection calculation of each feature, the prediction rating is obtained and the recommendation is generated. This paper uses MovieLens 1M data set and Amazon Digital Music data set for experiments. The results show that compared with other deep learning-based recommendation models and traditional recommendation models, the model proposed in this paper has achieved better results in both MSE and MAE indicators.
- Statista statistics [DB/OL].https://www.statista.com/.Google Scholar
- Liu Kai, Zhang Limin, Zhou Lijun. Application Review of Deep Learning in information Recommendation System [J]. Minicomputer systems,2019,40(04):738-743.Google Scholar
- Zhang Min, DING Bhiyuan, MA Weizhi, TAN Yunzhi, Liu Yiqun, Ma Shaoping. Hybrid Recommendation Method based on Deep Learning Enhancement [J]. Journal of tsinghua university (natural science edition),2017,57(10):1014-1021.Google Scholar
- Li C , He M , Qaosar M , Capturing Temporal Dynamics of Users' Preferences from Purchase History Big Data for Recommendation System[C]. 2018 IEEE International Conference on Big Data (Big Data). IEEE, 2018.Google Scholar
- Hu Sicai, SUN Jiping, Ju Rooting, WANG Xia. A Hybrid Recommendation Algorithm Based on Deep neural Network and Probability Matrix Decomposition [J]. Journal of sichuan university (natural science edition), 2019,56(06):1033-1041.Google Scholar
- Senyurek V Y , Imtiaz M H , Belsare P , A CNN-GRU neural network for recognition of puffing in smoking episodes using wearable sensors[J]. Biomedical Engineering Letters, 2020(1).Google Scholar
- Chenbin Li, Guohua Zhan, Zhihua Li. News Text Classification Based on Improved Bi-GRU-CNN[C]. 2018 9th International Conference on Information Technology in Medicine and Education (ITME). 2018.Google Scholar
- zhou feiyan, jin linpeng, dong jun. Review of research on convolutional neural networks [J]. Journal of computer science,2017,40(06):1229-1251.Google Scholar
- Jin R , Lu L , Lee J , Multi-representational convolutional neural networks for text classification[J]. Computational Intelligence, 2019(11).Google Scholar
- Tang Wenbing, Ren Zhengyun, Han Fang. Collaborative Convolution Dynamic Recommendation Network based on attention Mechanism [J/OL].Automation: 1-11 [2020-09-22]Google Scholar
- Chen J, Abdul a. A session-based Customer Preference Learning Method by Using the Gated Recurrent Units with Attention Function[J]. IEEE Access, 2019,7(02):17750-17759.Google ScholarCross Ref
- Li Yandong, Hao Zongbo, Lei Hang. Research Overview of convolutional neural networks [J]. Computer application,2016,36(09):2508-2515+2565.Google Scholar
- GroupLens.MoviesLens[DB/OL].https://grouplens.org/datasets/MovieLens/.Google Scholar
- Amazon.Amazon_Review_Data(2018)[DB/OL].https://nijianmo.github.io/amazon/index.html.Google Scholar
- Ruan Wenjun, Hu Xiaolong, Li Lihua. Film Recommendation Algorithm based on Deep Learning [J]. Journal of hubei university (natural science edition),2020,42(02):136-141.Google Scholar
- Jiang S, Zhang L, Zhang Z. New Collaborative Filtering Algorithm Based on Relative Similarity[J]. 2016.Google Scholar
- Koren Y , Bell R , Volinsky C . Matrix Factorization Techniques for Recommender Systems[J]. Computer, 2009, 42(8):30-37.Google ScholarDigital Library
Recommendations
Deep Recommendation Model Based on Local Attention and GRU
ICIAI '21: Proceedings of the 2021 5th International Conference on Innovation in Artificial IntelligenceThe recommendation systems are dedicated to providing people with valuable information by information filtering. Although the recommendation models based on matrix decomposition are widely used, they perform poorly in the case of sparse data. The review-...
Collaborative Filtering Recommendation Model based on Convolutional Denoising Auto Encoder
ChineseCSCW '17: Proceedings of the 12th Chinese Conference on Computer Supported Cooperative Work and Social ComputingSparse matrix problem and cold-start problem have been major challenges for recommendation systems. Many approaches take advantage of the combination of Denosing Auto Encoder (DAE) and Collaborative Filtering (CF) methods to address the above problems. ...
Mutual Self Attention Recommendation with Gated Fusion Between Ratings and Reviews
Database Systems for Advanced ApplicationsAbstractProduct ratings and reviews can provide rich useful information of users and items, and are widely used in recommender systems. However, it is nontrivial to infer user preference according to the history behaviors since users always have different ...
Comments