Answers are grounded in this paper and cite their sources.
Demonstrates improved news recommendation in users, suggesting enhanced personalization techniques.
With the explosion of information in the Internet age, news recommendation uses various technologies to explore user interests and provide users with personalized news matching in order to reduce the load of user information. ID-based algorithms such as content-based recommendation and collaborative filtering are not very suitable for news recommendation. Because of the iterative speed of news, a large number of new items will be generated in a short time, and it will also replace outdated news. It will face data sparseness and Problems such as cold start have certain limitations. This paper uses knowledge-based convolutional neural network and hierarchical attention mechanism to obtain the feature text representation of news text, and combines these features to learn that users are responsible for behavioral data to provide new recommendations. We have conducted experiments on real news data sets, and the results show that our model is significantly better than the benchmark method.
No takes yet. Share an insight, caveat, or question.
Cheng et al. (2021) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: