Design of news recommendation model based on sub-attention news encoder

• Published in: PeerJ. Computer science Vol. 9; p. e1246
• Main Author: Zhang, Wenting
• Format: Journal Article
• Language: English
• Published: United States PeerJ. Ltd 09.03.2023; PeerJ, Inc; PeerJ Inc
• Subjects: Analysis; Artificial Intelligence; Artificial neural networks; CNN; Coders; Collaboration; Computer Networks and Communications; Feature extraction; Information overload; Learning; Multi-head self-attention mechanism; Multimedia; Neural networks; News; News recommendation; Preferences; Rankings; Ratings & rankings; Recommender systems; Researchers; Semantics; Sub-attention; Text Mining; Multi-head self-attention mechanism; Sub-attention; CNN; News recommendation
• ISSN: 2376-5992; 2376-5992
• DOI: 10.7717/peerj-cs.1246

To extract finer-grained segment features from news and represent users accurately and exhaustively, this article develops a news recommendation (NR) model based on a sub-attention news encoder. First, by using convolutional neural network (CNN) and sub-attention mechanism, this model extracts a rich feature matrix from the news text. Then, from the perspective of image position and channel, the granular image data is retrieved. Next, the user's news browsing history is injected with a multi-head self-attention mechanism, and time series prediction is applied to the user's interests. Finally, the experimental results show that the proposed model performs well on the indicators: mean reciprocal rank (MRR), Normalized Discounted Cumulative Gain (NDCG) and area under the curve (AUC), with an average increase of 4.18%, 5.63% and 6.55%, respectively. The comparative results demonstrate that the model performs best on a variety of datasets and has fastest convergence speed in all cases. The proposed model may provide guidance for the design of the news recommendation system in the future.