Abstract
Review-based recommender suffers from the sparsity of reviews: only a few users leave substantial comments in the real world. As a result, some recent methods resort to supplementary reviews written by similar users, which only leverage homogeneous preferences. However, users holding different views could also supply valuable information with heterogeneous preferences. In this paper, we propose a recommendation model for rating prediction, named Heterogeneous Review-based Recommendation via Four-way Attention (HRFA). To take advantage of the heterogeneous preferences, the supplementary reviews in HRFA are redefined as reviews from all users with common purchase history, no matter whether they give similar ratings. Specially, we integrate the heterogeneous preferences into the one semantic space via introducing a similarity projection based on rating difference. Experiments conducted on five datasets demonstrate that our model achieves higher rating prediction accuracy than other baselines.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Catherine, R., Cohen, W.W.: Transnets: learning to transform for recommendation. In: RecSys, pp. 288–296 (2017)
Chen, C., Zhang, M., Liu, Y., Ma, S.: Neural attentional rating regression with review-level explanations. In: WWW, pp. 1583–1592 (2018)
Chin, J.Y., Zhao, K., Joty, S.R., Cong, G.: ANR: aspect-based neural recommender. In: CIKM, pp. 147–156. ACM (2018)
Dong, X., Ni, J., Cheng, W., Chen, Z., Zong, B., Song, D., Liu, Y., Chen, H., de Melo, G.: Asymmetrical hierarchical networks with attentive interactions for interpretable review-based recommendation. In: AAAI, pp. 7667–7674 (2020)
Guo, L., Shao, J., Tan, K., Yang, Y.: Wheretogo: personalized travel recommendation for individuals and groups. In: IEEE-MDM, pp. 49–58 (2014)
Hou, Y., Yang, N., Wu, Y., Yu, P.S.: Explainable recommendation with fusion of aspect information. World Wide Web 22(1), 221–240 (2018). https://doi.org/10.1007/s11280-018-0558-1
Kim, Y.: Convolutional neural networks for sentence classification. In: EMNLP, pp. 1746–1751 (2014)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)
Koren, Y., Bell, R.M., Volinsky, C.: Matrix factorization techniques for recommender systems. Computer 42(8), 30–37 (2009)
Li, C., Quan, C., Peng, L., Qi, Y., Deng, Y., Wu, L.: A capsule network for recommendation and explaining what you like and dislike. In: SIGIR, pp. 275–284 (2019)
Linden, G., Smith, B., York, J.: Industry report: Amazon.com recommendations: item-to-item collaborative filtering. IEEE Distrib. Syst. 4(1) (2003)
Liu, D., Li, J., Du, B., Chang, J., Gao, R.: DAML: dual attention mutual learning between ratings and reviews for item recommendation. In: SIGKDD, pp. 344–352 (2019)
Liu, H., et al.: NRPA: neural recommendation with personalized attention. In: SIGIR, pp. 1233–1236 (2019)
Luo, X., Zhou, M., Xia, Y., Zhu, Q.: An efficient non-negative matrix-factorization-based approach to collaborative filtering for recommender systems. IEEE Trans. Ind. Informatics 10(2), 1273–1284 (2014)
McAuley, J.J., Leskovec, J.: Hidden factors and hidden topics: understanding rating dimensions with review text. In: RecSys, pp. 165–172 (2013)
Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: ICML, pp. 807–814. Omnipress (2010)
Rendle, S.: Factorization machines. In: ICDM, pp. 995–1000 (2010)
Tang, Y., Guo, K., Zhang, R., Xu, T., Ma, J., Chi, T.: ICFR: an effective incremental collaborative filtering based recommendation architecture for personalized websites. World Wide Web 23(2), 1319–1340 (2020)
Wang, X., Xiao, T., Tang, J., Ouyang, D., Shao, J.: MRMRP: multi-source review-based model for rating prediction. In: DASFAA, pp. 20–35 (2020)
Wu, L., Quan, C., Li, C., Ji, D.: PARL: let strangers speak out what you like. In: CIKM, pp. 677–686 (2018)
Zheng, L., Noroozi, V., Yu, P.S.: Joint deep modeling of users and items using reviews for recommendation. In: WSDM, pp. 425–434 (2017)
Acknowledgements
This work was supported by NSFC grants (No. 61972155), the Science and Technology Commission of Shanghai Municipality (20DZ1100300) and the Open Project Fund from Shenzhen Institute of Artificial Intelligence and Robotics for Society, under Grant No. AC01202005020.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, S., Ji, W., Yuan, J., Wang, X. (2021). HRFA: Don’t Ignore Strangers with Different Views. In: Zhang, W., Zou, L., Maamar, Z., Chen, L. (eds) Web Information Systems Engineering – WISE 2021. WISE 2021. Lecture Notes in Computer Science(), vol 13081. Springer, Cham. https://doi.org/10.1007/978-3-030-91560-5_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-91560-5_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-91559-9
Online ISBN: 978-3-030-91560-5
eBook Packages: Computer ScienceComputer Science (R0)