Review-Based Topic Distribution Profile for Recommender Systems

  • Mala SaraswatEmail author
  • Shampa Chakraverty
  • Agrim Sharma
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 612)


Using social media and e-commerce sites, users convey their preferences and interests via reviews, feedback, and comments. These comments and reviews consist of details about a given product or an item and also users’ thoughts. Different features of user-generated content include various features such as emotions, sentiments, review usefulness, and so forth that exhibit a promising exploration in the domain of recommendation frameworks. This paper harness reviews as the content generated from user to exploit topics based on topic modeling using latent Dirichlet allocation for generating topic distribution profile of users. Examination of topic distribution profile of users gives us a new prospect for recommendation of products which is based on hidden thematic framework of user preferences. Assessment on books and movie dataset confirms the adequacy of the suggested topic distribution profile for recommendation system framework.


Reviews User-generated content Recommender systems Collaborative filtering Topic modeling 


  1. 1.
    Adomavicius G, Tuzhilin A (2005) Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions. IEEE Trans Knowl Data Eng 6:734–749CrossRefGoogle Scholar
  2. 2.
    Pazzani MJ, Billsus D (2007) Content-based recommendation systems. In: The adaptive web. Springer, Heidelberg, pp 325–341Google Scholar
  3. 3.
    Schafer J, Ben et al (2007) Collaborative filtering recommender systems. In: The adaptive web. Springer, Heidelberg, pp 291–324Google Scholar
  4. 4.
    Chen L, Chen G, Wang F (2015) Recommender systems based on user reviews: the state of the art. User Model User-Adap Inter 25(2):99–154CrossRefGoogle Scholar
  5. 5.
    Blei DM, Ng AY, Jordan MI (2003) Latent dirichlet allocation. J Mach Learn Res 3:993–1022Google Scholar
  6. 6.
    Boyd-Graber J, Blei D, Zhu X (2007) A topic model for word sense disambiguation. In: Proceedings of the 2007 joint conference on empirical methods in natural language processing and computational natural language learning (EMNLP-CoNLL)Google Scholar
  7. 7.
    Haghighi A, Vanderwende L (2009) Exploring content models for multi-document summarization. In: Proceedings of human language technologies: the 2009 annual conference of the north american chapter of the association for computational linguistics. Association for Computational LinguisticsGoogle Scholar
  8. 8.
    McAuley J, Leskovec J (2013) Hidden factors and hidden topics: understanding rating dimensions with review text. In: Proceedings of the 7th ACM conference on recommender systemsGoogle Scholar
  9. 9.
    Seroussi Y, Bohnert F, Zukerman I (2012) Authorship attribution with author-aware topic models. In: Proceedings of the 50th annual meeting of the association for computational linguistics: short papers-volume 2. Association for Computational LinguisticsGoogle Scholar
  10. 10.
    Harper FM, Konstan JA (2015) The MovieLens datasets: history and context. ACM Trans Interact Intell Syst (TiiS) 5(4) Article 19, 19p. Scholar
  11. 11.
    Ziegler C-N, McNee SM, Konstan JA, Lausen G (2005) Proceedings of the 14th international world wide web conference (WWW ’05), May 10–14, Chiba, JapanGoogle Scholar
  12. 12.
    Chakraverty S, Saraswat M (2017) Review based emotion profiles for cross domain recommendation. Multimed Tools Appl 76(24):25827–25850CrossRefGoogle Scholar
  13. 13.
    McCallum AK (2002)MALLET: a machine learning for language toolkit.

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Mala Saraswat
    • 1
    Email author
  • Shampa Chakraverty
    • 1
  • Agrim Sharma
    • 2
  1. 1.Department of Computer EngineeringNSUTNew DelhiIndia
  2. 2.Department of Information TechnologyNSUTNew DelhiIndia

Personalised recommendations