Learning a Concept Based Ranking Model with User Feedback

  • E. Umamaheswari
  • T. V. Geetha
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8284)


Automatically learning a ranking model is becoming an essential task for effective information retrieval. Its advantage lies in the ability to combine the user feedback with the conceptual features. However, learning to rank methods require large, training and test data sets, to gather feedback from the user. Existing learning-to-rank methods focus either on user feedback or at the document level or on query-dependent feature scores. In this paper, we consider the implicit and explicit feedback from the user using a set of test data. This test data is given as input to the training phase, in which we find the document conceptual and query-dependent document features. Hence, the impact of the user feedback on the search query is identified by learning the document, and query level conceptual features, using statistical methods. A DCG (Discounted Cumulative gain) score is calculated and used in comparing the ranking in subsequent iterations. The learning process continues until there is no change in the DCG score. The learned ranking model is compared with our base ranking method and achieved 20% improvements in nDCG score.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Li, H.: A short introduction to learning to rank. IEICE Transactions 94-D, 1854–1862 (2011)Google Scholar
  2. 2.
    Crammer, K., Singer, Y.: Pranking with ranking. In: NIPS, pp. 641–647 (2001)Google Scholar
  3. 3.
    Sellamanickam, S., Sundararajan, S., Garg, P., Selvaraj, S.K., Keerthi, S.S.: A pairwise ranking based approach to learning with positive and unlabeled examples. In: Proceedings of the 20th ACM International Conference on Information and Knowledge Management. CIKM 2011, pp. 663–672. ACM, New York (2011)Google Scholar
  4. 4.
    Xia, Fen, Liu, Yan, T., Wang, Jue, Zhang, Wensheng, Li, Hang: Listwise approach to learning to rank: theory and algorithm. In: Proceedings of the 25th International Conference on Machine Learning, ICML 2008, pp. 1192–1199. ACM, New York (2008)Google Scholar
  5. 5.
    Radlinski, F., Joachims, T.: Active exploration for learning rankings from clickthrough data. In: Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2007, pp. 570–579. ACM, New York (2007)Google Scholar
  6. 6.
    Joachims, T., Granka, L., Pan, B., Hembrooke, H., Gay, G.: Accurately interpreting clickthrough data as implicit feedback. In: In Proceedings of SIGIR, pp. 154–161 (2005)Google Scholar
  7. 7.
    Bai, B., Weston, J., Grangier, D., Collobert, R., Sadamasa, K., Qi, Y., Chapelle, O., Weinberger, K.: Learning to rank with (a lot of) word features. Inf. Retr. 13(3), 291–314 (2010)CrossRefGoogle Scholar
  8. 8.
    (Undl foundation) Universal Networking LanguagesGoogle Scholar
  9. 9.
    Balaji, J., Geetha, T.V., Ranjani, Karky, M.: Article: Morpho-semantic features for rule-based tamil enconversion. International Journal of Computer Applications 26, 11–18 (2011), Published by Foundation of Computer Science, New York, USACrossRefGoogle Scholar
  10. 10.
    Weixin, T., Fuxi, Z.: Learning to rank using semantic features in document retrieval. In: Proceedings of the 2009 WRI Global Congress on Intelligent Systems - Volume 3. GCIS 2009, pp. 500–504. IEEE Computer Society, Washington, DC (2009)Google Scholar
  11. 11.
    Kuo, Wei, J., Cheng, Pu-Jen, Wang, Hsin-Min.: Learning to rank from bayesian decision inference. In: Proceedings of the 18th ACM Conference on Information and Knowledge Management, CIKM 2009, pp. 827–836. ACM, New York (2009)Google Scholar
  12. 12.
    Xu, Jingfang, Chen, Chuanliang, Xu, Gu, Li, Hang, Abib, Torres, E.R.: Improving quality of training data for learning to rank using click through data. In: Proceedings of the Third ACM International Conference on Web Search and Data Mining, WSDM 2010, pp. 171–180. ACM, New York (2010)Google Scholar
  13. 13.
    Xue, Rong, G., Zeng, Jun, H., Chen, Zheng, Yu, Yong, Ma, Ying, W., Xi, WenSi, Fan, W.: Optimizing web search using web click through data. In: Proceedings of the Thirteenth ACM International Conference on Information and Knowledge Management, CIKM 2004, pp. 118–126. ACM, New York (2004)Google Scholar
  14. 14.
    Chen, N., Prasanna, V.K.: Learning to rank complex semantic relationships. Int. J. Semantic Web Inf. Syst. 8(4), 1–19 (2012)CrossRefGoogle Scholar
  15. 15.
    Umamaheswari, E., Geetha, T.V., Parthasarathi, R., Karky, M.: A multilevel unl concept based searching and ranking. In: WEBIST 2011, pp. 282–289 (2011)Google Scholar
  16. 16.
    Subalalitha, T.V., Geetha, P.R., Karky, M.: Corex: A concept based semantic indexing technique. In: SWM 2008 (2008)Google Scholar
  17. 17.
    K, E., Geetha, T.V., Parthasarathi, R., Karky, M.: Core concept based query expansion, internet coimbatore tamil conference. In: Proceedings of World Classical Tamil Conference, Coimbatore (2010) Google Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  • E. Umamaheswari
    • 1
  • T. V. Geetha
    • 1
  1. 1.Department of Computer Science and EngineeringAnna UniversityChennaiIndia

Personalised recommendations