Unsupervised Topic Extraction for the Reviewer’s Assistant

  • Ruihai Dong
  • Markus Schaal
  • Michael P. O’Mahony
  • Kevin McCarthy
  • Barry Smyth
Conference paper


User generated reviews are now a familiar and valuable part of most ecommerce sites since high quality reviews are known to influence purchasing decisions. In this paper we describe work on the Reviewer’s Assistant (RA), which is a recommendation system that is designed to help users to write better reviews. It does this by suggesting relevant topics that they may wish to discuss based on the product they are reviewing and the content of their review so far. We build on prior work and describe an unsupervised topic extraction module for the RA system that enhances the system’s ability to automatically adapt to new content categories and application domains. Our main contribution includes the results of a controlled, live-user study to show that the RA system is capable of supporting users to create reviews that enjoy higher quality ratings than Amazon’s own high quality reviews, even without using manually created topic models.


Association Rule Latent Dirichlet Allocation Online Review Product Review Review Quality 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Agrawal, R., Imieli’nski, T., Swami, A.: Mining Association Rules between Sets of Items in Large Databases. ACM SIGMOD Record 22(May), 207–216 (1993)Google Scholar
  2. 2.
    Agrawal, R., Srikant, R.: Fast Algorithms for Mining Association Rules in Large Databases. In: Proceedings of the 20th International Conference on Very Large Data Bases, VLDB ’94, pp. 487–499. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA (1994)Google Scholar
  3. 3.
    Blei, D.M.: Probabilistic topic models. Commun. ACM 55(4), 77–84 (2012). DOI 10.1145/ 2133806.2133826CrossRefGoogle Scholar
  4. 4.
    Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993– 1022 (2003)MATHGoogle Scholar
  5. 5.
    Bridge, D., Waugh, A.: Using Experience on the Read/Write Web: The GhostWriter System. In: D. Bridge, E. Plaza, N. Wiratunga (eds.) Procs. of WebCBR: The Workshop on Reasoning from Experiences on the Web (Workshop Programme of the Eighth International Conference on Case-Based Reasoning), pp. 15–24 (2009)Google Scholar
  6. 6.
    Dong, R., McCarthy, K., O’Mahony, M.P., Schaal, M., Smyth, B.: Towards an Intelligent Reviewer’s Assistant: Recommending Topics to Help Users to Write Better Product Reviews. In: Procs. of IUI: 17th International Conference on Intelligent User Interfaces, Lisbon, Portugal, February 14-17, 2012, pp. 159–168 (2012)Google Scholar
  7. 7.
    Dong, R., Schaal, M., O’Mahony, M.P., McCarthy, K., Smyth, B.: Harnessing the Experience Web to Support User-Generated Product Reviews. In: 20th International Conference on Case- Based Reasoning, Lyon, France (2012). To appear.Google Scholar
  8. 8.
    Gretarsson, B., O’Donovan, J., Bostandjiev, S., H‥ollerer, T., Asuncion, A.U., Newman, D., Smyth, P.: Topicnets: Visual analysis of large text corpora with topic modeling. ACM TIST 3(2), 23 (2012)Google Scholar
  9. 9.
    Healy, P., Bridge, D.: The GhostWriter-2.0 System: Creating a Virtuous Circle in Web 2.0 Product Reviewing. In: D. Bridge, S.J. Delany, E. Plaza, B. Smyth, N.Wiratunga (eds.) Procs. of WebCBR: The Workshop on Reasoning from Experiences on the Web (Workshop Programme of the 18th International Conference on Case-Based Reasoning), pp. 121–130 (2010)Google Scholar
  10. 10.
    Hu, N., Liu, L., Zhang, J.: Do online reviews affect product sales? the role of reviewer characteristics and temporal effects. Information Technology and Management 9, 201–214 (2008).10.1007/s10799-008-0041-2CrossRefGoogle Scholar
  11. 11.
    Kim, S.M., Pantel, P., Chklovski, T., Pennacchiotti, M.: Automatically assessing review helpfulness. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2006), pp. 423–430. Sydney, Australia (2006)Google Scholar
  12. 12.
    Liu, Y., Huang, X., An, A., Yu, X.: Modeling and predicting the helpfulness of online reviews. In: Proceedings of the 2008 Eighth IEEE International Conference on Data Mining (ICDM 2008), pp. 443–452. IEEE Computer Society, Pisa, Italy (2008)Google Scholar
  13. 13.
    O’Mahony, M.P., Smyth, B.: Learning to recommend helpful hotel reviews. In: Proceedings of the third ACM conference on Recommender Systems, RecSys ’09, pp. 305–308. ACM (2009). DOI 10.1145/1639714.1639774Google Scholar
  14. 14.
    Schaal, M., M‥uller, R.M., Brunzel, M., Spiliopoulou, M.: RELFIN - Topic Discovery for Ontology Enhancement and Annotation. In: ESWC’05, pp. 608–622 (2005)Google Scholar
  15. 15.
    Zhu, F., Zhang, X.M.: Impact of online consumer reviews on sales: The moderating role of product and consumer characteristics. Journal of Marketing 74(2), 133–148 (2010)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London 2012

Authors and Affiliations

  • Ruihai Dong
    • 1
  • Markus Schaal
    • 1
  • Michael P. O’Mahony
    • 1
  • Kevin McCarthy
    • 1
  • Barry Smyth
    • 1
  1. 1.Centre for Sensor Web TechnologiesUniversity College DublinDublinIreland

Personalised recommendations