Abstract
It is a common way to represent paper properties as a heterogeneous academic network graph, such as authorships, citations, by which the latent features of paper can be learnt. To better integrate both text and structural features, we propose the joint embedding method for paper recommendation. We adopt a pre-trained language model to learn the paper semantic features from titles, and adopt a graph convolution network to extract the structural features from the constructed academic network graph. These two embeddings are combined together through the attention mechanism as a joint one. To clarify the real negative samples on uncited papers, we introduce some expert rules as the selection strategy on samples in model training, which can exclude the far-unrelated negative samples and potential positive samples. User interests are modeled by their historical publications and references and thus papers are recommended according to the relatedness between user interests and paper embeddings. We conduct experiments on the ACM academic paper dataset. The results show that our model outperforms baseline methods on personalized recommendation. We also analyze the influence of model structure and parameter setting. The results show that our sample strategy effectively improves the precision of recommendation, which illustrate that the strategy enhances the quality of training data.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Xie, Y., Wang, S., Pan, W., Tang, H., Sun, Y.: Embedding based personalized new paper recommendation. In: Sun, Y., Liu, D., Liao, H., Fan, H., Gao, L. (eds.) Chinese CSCW 2020. CCIS, vol. 1330, pp. 558–570. Springer, Singapore (2021). https://doi.org/10.1007/978-981-16-2540-4_40
Zhu, Y., Lin, Q., Lu, H.: Recommending scientific paper via heterogeneous knowledge embedding based attentive recurrent neural networks. Knowl. Based Syst. 215, 106744 (2021)
Gautam, J., Kumar, E.: An improved framework for tag-based academic information sharing and recommendation system. In: Proceedings of the World Congress on Engineering, U.K., pp. 1–6 (2012)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv: Computation and Language (2018)
Jeong, C., Jang, S., Park, E., Choi, S.: A context-aware citation recommendation model with BERT and graph convolutional networks. Scientometrics 124(3), 1907–1922 (2020). https://doi.org/10.1007/s11192-020-03561-y
Tao, M., Yang, X., Gu, G., Li, B.: Paper recommend based on LDA and PageRank. In: Sun, X., Wang, J., Bertino, E. (eds.) ICAIS 2020. CCIS, vol. 1254, pp. 571–584. Springer, Singapore (2020). https://doi.org/10.1007/978-981-15-8101-4_51
Koren, Y.: Factorization meets the neighborhood: a multifaceted collaborative filtering model. In: Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, USA, pp. 426–434 (2008)
Sugiyama, K., Kan, M.Y.: Exploiting potential citation papers in scholarly paper recommendation. In: Proceedings of the 13th ACM/IEEE-CS Joint Conference on Digital Libraries, pp. 153–162 (2013)
Guo, G., Zhang, J., Yorke-Smith, N.: Leveraging multiviews of trust and similarity to enhance clustering-based recommender systems. Knowl. Based Syst. 74, 14–27 (2015)
Wang, H., Zhang, F., Xie, X, Guo, M.: DKN: deep knowledge-aware network for news recommendation. In: Proceedings of the 2018 World Wide Web Conference, pp. 1835–1844 (2018)
Yu, X., Ren, X., Sun, Y., et al.: Personalized entity recommendation: a heterogeneous information network approach. In: Proceedings of the 7th ACM International Conference on Web Search and Data Mining, pp. 283–292 (2014)
Wang, H., Zhang, F., Wang, J., et al.: RippleNet: propagating user preferences on the knowledge graph for recommender systems. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management, Italy, pp. 417–426 (2018)
Wang, H., Zhao, M., Xie, X., et al.: Knowledge graph convolutional networks for recommender systems. In: Proceedings of the World Wide Web Conference, USA, pp. 3307–3313 (2019)
Wang, H., Zhang, F., Zhang, M., et al.: Knowledge-aware graph neural networks with label smoothness regularization for recommender systems. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, USA, pp. 968–977 (2019)
Wang, X., Wang, D., Xu, C., et al.: Explainable reasoning over knowledge graphs for recommendation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 01, pp. 5329–5336 (2019)
Pan, L., Dai, X., Huang, S., Chen, J.: Academic paper recommendation based on heterogeneous graph. In: Sun, M., Liu, Z., Zhang, M., Liu, Y. (eds.) CCL/NLP-NABD -2015. LNCS (LNAI), vol. 9427, pp. 381–392. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-25816-4_31
Manju, G., Abhinaya, P., Hemalatha, M.R., Manju, G.G.: Cold start problem alleviation in a research paper recommendation system using the random walk approach on a heterogeneous user-paper graph. Int. J. Intell. Inf. Technol. (IJIIT) 16(2), 24–48 (2020)
Kong, X., Mao, M., Wang, W., et al.: VOPRec: vector representation learning of papers with text information and structural identity for recommendation. IEEE Trans. Emerg. Top. Comput. 9, 226–237 (2018)
Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using siamese BERT-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 3982–3992 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, W., Xie, Y., Sun, Y. (2022). Joint Embedding Multiple Feature and Rule for Paper Recommendation. In: Sun, Y., et al. Computer Supported Cooperative Work and Social Computing. ChineseCSCW 2021. Communications in Computer and Information Science, vol 1492. Springer, Singapore. https://doi.org/10.1007/978-981-19-4549-6_5
Download citation
DOI: https://doi.org/10.1007/978-981-19-4549-6_5
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-4548-9
Online ISBN: 978-981-19-4549-6
eBook Packages: Computer ScienceComputer Science (R0)