Advertisement

Applied Intelligence

, Volume 49, Issue 7, pp 2623–2640 | Cite as

Distributed representations based collaborative filtering with reviews

  • Xinghua ZhengEmail author
  • Wen He
  • Lei Li
Article

Abstract

Review texts, which have been shown helpful for recommending items for users, are often available in the form of user feedback for items. Despite the success of previous approaches exploring reviews for recommendations, they are all based on long review texts. The users reviews are, however, often short in real-world applications. In this paper, we develop a novel approach to leverage information from short review texts for recommendation based on word vector representations. We first build word vectors to represent items and users, which are called item-vector and user-vector, respectively. After that we concatenate item-vectors and user-vectors to form a set of training data with the rating scores that users give to items. Finally we train a regression model to predict the unknown rating scores. In our experiment, we show that our approach is effective, compared to state-of-the-art algorithms.

Keywords

Recommender system Distributed representation Short reviews 

Notes

References

  1. 1.
    McAuley JJ, Leskovec J (2013) From amateurs to connoisseurs: modeling the evolution of user expertise through online reviews. In: Proceedings of the 22nd international world wide web conference, pp 897–908Google Scholar
  2. 2.
    Lerman K, Blair-Goldensohn S, McDonald RT (2009) Sentiment summarization: evaluating and learning user preferences. In: Proceedings of EACL, pp 514–522Google Scholar
  3. 3.
    Sharma A, Cosley D (2013) Do social explanations work?: studying and modeling the effects of social explanations in recommender systems. In: Proceedings of the 22nd international world wide web conference, pp 1133–1144Google Scholar
  4. 4.
    Petz G, Karpowicz M, Fürschuß H, Auinger A, Stríteský V., Holzinger A (2015) Reprint of: computational approaches for mining user’s opinions on the Web 2.0. Inf Process Manage 51(4):510–519CrossRefGoogle Scholar
  5. 5.
    Ganu G, Elhadad N, Marian AM (2009) Beyond the stars: Improving rating predictions using review text content. In: Proceedings of the 12th international workshop on the web and databases, pp 443–451Google Scholar
  6. 6.
    Agarwal D, Chen B-C (2010) fLDA: matrix factorization through latent dirichlet allocation. In: Proceedings of the 3rd international conference on web search and web data mining, pp 91–100Google Scholar
  7. 7.
    Wang C, Blei DM (2011) Collaborative topic modeling for recommending scientific articles. In: Proceedings of the 17th ACM SIGKDD international conference on knowledge discovery and data mining, pp 448–456Google Scholar
  8. 8.
    McAuley JJ, Leskovec J, Wang C, Blei DM (2013) Hidden factors and hidden topics: understanding rating dimensions with review textCollaborative topic modeling for recommending scientific articles. In: Proceedings of the 7th ACM conference on recommender systems, pp 165–172Google Scholar
  9. 9.
    Ling G, Lyu MR, King I, Blei DM (2014) Ratings meet reviews, a combined approach to recommend. In: Proceedings of RecSys, pp 105–112Google Scholar
  10. 10.
    Zhao F, Xiao M, Guo Y (2016) Predictive collaborative filtering with side information. In: Proceedings of IJCAI, pp 435–447Google Scholar
  11. 11.
    Turian JP, Ratinovand L-A, Bengio Y (2010) Word representations: A simple and general method for semi-supervised learning. In: Proceedings of the 48th annual meeting of the association for computational linguistics, pp 384–394Google Scholar
  12. 12.
    Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: Proceedings of advances in neural information processing systems, pp 3111–3119Google Scholar
  13. 13.
    Le QV, Mikolov T (2014) Distributed representations of sentences and documentsy. In: Proceedings of the 31th international conference on machine learning, pp 1188–1196Google Scholar
  14. 14.
    Huang W, Zhaohui WU, Liang C, Mitra P, Lee Giles C (2015) A neural probabilistic model for context based citation recommendation. In: Proceedings of AAAI, pp 968–977Google Scholar
  15. 15.
    Koren Y, Bell RM, Volinsky C (2009) Matrix factorization techniques for recommender systems. IEEE Comput 42(8):30–37CrossRefGoogle Scholar
  16. 16.
    Diao Q, Qiu M, Smola AJ, Jiang J, Wan C (2014) Jointly modeling aspects, ratings and sentiments for movie recommendation. In: Proceedings of the 20th ACM SIGKDD international conference on knowledge discovery and data mining, pp 193–202Google Scholar
  17. 17.
    Blei DM, Ng AY, Jordan MI (2003) Latent Dirichlet Allocation. J Mach Learn Res 3:193–202zbMATHGoogle Scholar
  18. 18.
    Koren Y, Bell RM (2011) Advances in collaborative filtering. Recommender systems handbook, pp 145–186Google Scholar
  19. 19.
    Wang S, Li F, Zhang M (2011) Supervised topic model with consideration of user and item. Late-breaking developments in the field of artificial intelligence, pp 315–324Google Scholar
  20. 20.
    Mesnil GR, Mikolov T, Marc’Aurelio R, Bengio Y (2014) Ensemble of generative and discriminative techniques for sentiment analysis of movie reviews. In: Proceedings of CoRR, arXiv:1412.5335
  21. 21.
    Xin X, Liu Z, Lin C-Y, Huang H, Wei X, Guo P (2015) Cross-domain collaborative filtering with review text. In: Proceedings of the 24th international joint conference on artificial intelligence, pp 1827–1834Google Scholar
  22. 22.
    Guang-Neng HU, Dai X-Y, Song Y, Huang S, Chen J (2015) A synthetic approach for recommendation: combining ratings, social relations, and reviews. In: Proceedings of the 24th international joint conference on artificial intelligence, pp 1756–1762Google Scholar
  23. 23.
    Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: Advances in neural information processing systems, pp 3111–3119Google Scholar
  24. 24.
    Morin F, Bengio Y (2005) Hierarchical probabilistic neural network language model. In: Proceedings of the international workshop on artificial intelligence and statistics, pp 246–252Google Scholar
  25. 25.
    Breiman L (2001) Random forests. Mach Learn 45(1):5–32CrossRefzbMATHGoogle Scholar
  26. 26.
    Xue H-J, Dai X, Zhang J, Huang S, Chen J (2017) Deep matrix factorization models for recommender systems. In: Proceedings of the 26th international joint conference on artificial intelligence, pp 3203–3209Google Scholar
  27. 27.
    Fang H, Zhen Z, Shao Y, Hsieh C-J (2017) Improved bounded matrix completion for large-scale recommender systems. In: Proceedings of the 26th international joint conference on artificial intelligence, pp 1654–1660Google Scholar
  28. 28.
    Wang Y, Wang S, Tang J, Qi G-J, Liu H, Li B (2017) CLARE: A joint approach to label classification and tag recommendation. In: Proceedings of the 31st conference on artificial intelligence, pp 210–216Google Scholar
  29. 29.
    Gao L, Wu J, Zhou C, Hu Y (2017) Collaborative dynamic sparse topic regression with user profile evolution for item recommendation. In: Proceedings of the 31st conference on artificial intelligence, pp 1316–1322Google Scholar
  30. 30.
    Li D, Chen C, Lv Q, Shang L, Chu SM, Zha H (2017) ERMMA: Expected risk minimization for matrix approximation-based recommender systems. In: Proceedings of the 21st conference on artificial intelligence, pp 1403–1409Google Scholar
  31. 31.
    Wang H, Wu Q, Wang H (2017) Factorization bandits for interactive recommendation. In: Proceedings of the 31st conference on artificial intelligence, pp 2695–2702Google Scholar
  32. 32.
    Sedhain S, Menon AK, Sanner S, Xie L, Braziunas D (2017) Low-rank linear cold-start recommendation from social data. In: Proceedings of the 31st conference on artificial intelligence, pp 1502–1508Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of Data and Computer ScienceSun Yat-sen UniversityGuangzhouChina

Personalised recommendations