Abstract
An important goal of online news system is to provide accurate personalized recommendation for users from mass news. One of the main problems in news recommendation is to obtain accurate news representation. Generally speaking, news is full of intellectual entities and common sense. However, existing news recommendation tends to ignore external knowledge and fail to fully detect potential knowledge links between news. In addition, news recommendation also faces the problem of user interest diversity. To solve the above problems, this paper proposes a knowledge enhancement and attention network based bnews recommendation model (KEAN) to enhance news title representation and user interest. The proposed model is mainly processed from two perspectives. First, for news titles, the entity embedding is enriched by aggregating information from its neighborhood in the knowledge graph, so as to obtain richer contextual embedding. Secondly, in order to meet the different interests in users, attention network is used to dynamically aggregate the information which is related to the current candidate news in user history. KEAN model can get rich feature representation by dealing with the correlation between entities and users’ interests. The experimental results show that the proposed model performs better than the other compared models with F1 and AUC being increased by 0.8%–1.2%, 0.6%–1.8% in Bing News and MIND dataset.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Okura, S., Tagami, Y., Ono, S., Tajima, A.: Embedding-based news recommendation for millions of users, pp. 1933–1942. ACM (2017)
Bansal, T., Das, M., Bhattacharyya, C.: Content driven user profiling for comment-worthy recommendations of news and blog articles, pp. 195–202. ACM (2015)
Liu, D., et al.: KRED: knowledge-aware document representation for news recommendations, pp. 200–209. ACM (2020)
Wang, H., Zhang, F., Zhang, M., Li, W., Wang, Z.: Knowledge-aware graph neural networks with label smoothness regularization for recommender systems, pp. 968–977. ACM (2019)
Wang, H., Zhang, F., Xie, X., Guo, M.: DKN: deep knowledge-aware network for news recommendation. In: 2018 World Wide Web Conference, pp. 1835–1844 (2018)
Kim, Y.: Convolutional neural networks for sentence classification. In: EMNLP (2014)
Niepert, M., Ahmed, M., Kutzkov, K.: Learning convolutional neural networks for graphs. In: The International Conference on Machine Learning, pp. 2014–2023 (2016)
Duvenaud, D.K., et al.: Convolutional networks on graphs for learning molecular fingerprints. In: Neural Information Processing Systems, pp. 2224–2232 (2015)
Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: Neural Information Processing Systems, pp. 1024–1034 (2017)
Wang, X., He, X., Cao, Y., Chua, T.-S.: KGAT: knowledge graph attention network for recommendation, pp. 950–958. ACM (2019)
Zhu, Q., Zhou, X., Song, Z., et al.: DAN: deep attention neural network for news recommendation. In: AAAI (2019)
Mingxiao, An., et al.: Neural news recommendation with long- and short-term user representations. In: The Annual Meeting of the Association for Computational Linguistics (2019)
Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: Advances in Neural Information Processing Systems, pp. 2787–2795 (2013)
Wang, Z., Zhang, J., Feng, J., Chen, Z.: Knowledge graph embedding by translating on hyperplanes. In: AAAI, pp. 1112–1119 (2014)
Ji, G., He, S., Xu, L., Liu, K., Zhao, J.: Knowledge graph embedding via dynamic mapping matrix. In: ACL, pp. 687–696 (2015)
Lin, Y., Liu, Z., Sun, M., Liu, Y., Zhu, X.: Learning entity and relation embeddings for knowledge graph completion. In: AAAI (2015)
Kingma, D., Ba, J.: Adam: a method for stochastic optimization (2014)
Kim, Y.: Convolutional neural networks for sentence classification. In: Empirical Methods in Natural Language Processing, pp. 1746–1751 (2014)
Wang, J, Wang, Z, Zhang, D, et al.: Combining knowledge with deep convolutional neural networks for short text classification. In: AAAI (2017)
Xue, H.J., Dai, X., Zhang, J., et al.: Deep matrix factorization models for recommender systems. In: AAAI (2017)
Guo, X., Lin, W., Li, Y.: DKEN: deep knowledge-enhanced network for recommender systems. Inform. Sci. 540, 263–277 (2020)
Cheng, H.T., Koc, L., Harmsen, J., et al.: Wide & Deep Learning for Recommender Systems, pp. 7–10. ACM (2016)
Steffen, R.: Factorization Machines with libFM. ACM (2012)
Ma, P., Gao, Q., Fan, J.: Context aware feature interaction based recommendation system. In: IRC, pp. 485–489 (2020)
Zhang, C., Li, T., Gou, Y., Yang, M.: KEAN: knowledge embedded and attention-based network for POI recommendation. In: ICAICE (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, Y., Gao, Q., Fan, J. (2022). KEAN: Knowledge-Enhanced and Attention Network for News Recommendation. In: Memmi, G., Yang, B., Kong, L., Zhang, T., Qiu, M. (eds) Knowledge Science, Engineering and Management. KSEM 2022. Lecture Notes in Computer Science(), vol 13368. Springer, Cham. https://doi.org/10.1007/978-3-031-10983-6_34
Download citation
DOI: https://doi.org/10.1007/978-3-031-10983-6_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-10982-9
Online ISBN: 978-3-031-10983-6
eBook Packages: Computer ScienceComputer Science (R0)