Discounted Cumulated Gain Based Evaluation of Multiple-Query IR Sessions

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4956)


IR research has a strong tradition of laboratory evaluation of systems. Such research is based on test collections, pre-defined test topics, and standard evaluation metrics. While recent research has emphasized the user viewpoint by proposing user-based metrics and non-binary relevance assessments, the methods are insufficient for truly user-based evaluation. The common assumption of a single query per topic and session poorly represents real life. On the other hand, one well-known metric for multiple queries per session, instance recall, does not capture early (within session) retrieval of (highly) relevant documents. We propose an extension to the Discounted Cumulated Gain (DCG) metric, the Session-based DCG (sDCG) metric for evaluation scenarios involving multiple query sessions, graded relevance assessments, and open-ended user effort including decisions to stop searching. The sDCG metric discounts relevant results from later queries within a session. We exemplify the sDCG metric with data from an interactive experiment, we discuss how the metric might be applied, and we present research questions for which the metric is helpful.


Interactive IR evaluation metrics cumulated gain 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bates, M.: The design of Browsing and Berrypicking Techniques for the Online Search Interface. Online Review 13(5), 407–424 (1989)CrossRefGoogle Scholar
  2. 2.
    Beaulieu, M., Robertson, S., Rasmussen, E.: Evaluating Iinteractive Systems in TREC. Journal of the American Society for Information Science 47(1), 85–94 (1996)CrossRefGoogle Scholar
  3. 3.
    Ingwersen, P., Järvelin, K.: The Turn: Integration of Information Seeking and Retrieval in Context. Springer, Dortrecht (2005)zbMATHGoogle Scholar
  4. 4.
    Järvelin, K., Kekäläinen, J.: IR Evaluation Methods for Retrieving Highly Relevant Documents. In: 23rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 41–48. ACM Press, New York (2000)CrossRefGoogle Scholar
  5. 5.
    Järvelin, K., Kekäläinen, J.: Cumulated Gain-based Evaluation of IR Techniques. ACM Transactions on Information Systems 20(4), 422–446 (2002)CrossRefGoogle Scholar
  6. 6.
    Kekäläinen, J.: Binary and Graded Relevance in IR Evaluations – Comparison of the Effects on Ranking of IR Systems. Inform. Processing & Management 41(5), 1019–1033 (2005)CrossRefGoogle Scholar
  7. 7.
    Over, P.: TREC-7 interactive track report. In: NIST Special Publication 500-242: The Seventh Text Retrieval Conference, NIST, Gaithersburg (1999)Google Scholar
  8. 8.
    Price, S.L., Lykke Nielsen, M., Delcambre, L.M.L., Vedsted, P.: Semantic Components Enhance Retrieval of Domain-Specific Documents. In: 16th ACM conference on Conference on information and knowledge management, pp. 429–438. ACM Press, New York (2007)CrossRefGoogle Scholar
  9. 9.
    Voorhees, E.: Evaluation by highly relevant documents. In: 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 74–82. ACM Press, New York (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  1. 1.University of TampereFinland
  2. 2.Portland State UniversityUSA
  3. 3.Royal School of Library and Information ScienceDenmark

Personalised recommendations