ABSTRACT
Recently, there has been considerable interest in the use of historical logged user interaction data—queries and clicks—for evaluation of search systems in the context of counterfactual analysis [8,10]. Recent approaches attempt to de-bias the historical log data by conducting randomization experiments and modeling the bias in user behavior. Thus far, the focus has been on addressing bias that arises due to the position of the document being clicked (position-bias) or sparsity of clicks on certain query-document pairs (selection-bias). However, there is another source of bias that could arise: the bias due to the context in which a document was presented to the user. The propensity of the user clicking on a document depends not only on its position but also on many other contextual factors. In this work, we show that the existing counterfactual estimators fail to capture one type of bias, specifically, the effect on click-through rates due to the relevance of documents ranked above. Further, we propose a modification to the existing estimator that takes into account this bias. We rely on full result randomization that allows us to control for the click context at various ranks; we demonstrate the effectiveness of our methods in evaluating retrieval system through experiments on a simulation setup that is designed to cover a wide variety of scenarios.
- B. Carterette and P. Chandar. O#ine Comparative Evaluation with Incremental, Minimally-Invasive Online Feedback. Proc. of SIGIR '18, 2018. Google ScholarDigital Library
- O. Chapelle, D. Metlzer, Y. Zhang, and P. Grinspan. Expected reciprocal rank for graded relevance. In Proceedings of the 18th ACM Conference on Information and Knowledge Management, CIKM '09, pages 621--630, 2009. Google ScholarDigital Library
- O. Chapelle and Y. Zhang. A dynamic bayesian network click model for web search ranking. 2009.Google ScholarDigital Library
- A. Chuklin, I. Markov, and M. de Rijke. Click Models for Web Search. Synthesis Lectures on Information Concepts, Retrieval, and Services, 7(3):1--115, 2015.Google Scholar
- N. Craswell, O. Zoeter, M. J. Taylor, and B. Ramsey. An experimental comparison of click position-bias models. WSDM, page 87, 2008. Google ScholarDigital Library
- G. E. Dupret and B. Piwowarski. A user browsing model to predict search engine click data from past observations. In Proceedings of the 31st Annual International ACM, SIGIR '08, pages 331--338, 2008. Google ScholarDigital Library
- T. Joachims, L. a. Granka, B. Pan, H. Hembrooke, F. Radlinski, and G. Gay. Evaluating the accuracy of implicit feedback from clicks and query reformulations in Web search. ACM Transactions on Information Systems, 25(2):7--es, 2007. Google ScholarDigital Library
- T. Joachims, A. Swaminathan, and T. Schnabel. Unbiased Learning-to-Rank with Biased Feedback. In Proceedings of the Tenth ACM International Conference on Web Search and Data Mining - WSDM '17, 2017. Google ScholarDigital Library
- M. T. Keane and M. O'Brien. Click Models for Web Search. In Proceedings of the Annual Meeting of the Cognitive Science Society, volume 28, 2006.Google Scholar
- X. Wang, M. Bendersky, D. Metzler, and M. Najork. Learning to Rank with Selection Bias in Personal Search. pages 115--124, 2016. Google ScholarDigital Library
- X. Wang, N. Golbandi, M. Bendersky, D. Metzler, and M. Najork. Position bias estimation for unbiased learning to rank in personal search. In Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, WSDM '18, pages 610--618, 2018. Google ScholarDigital Library
- Y. Yue, R. Patel, and H. Roehrig. Beyond position bias: Examining result attractiveness as a source of presentation bias in clickthrough data. In Proc. of WWW'10, pages 1011--1018, 2010. Google ScholarDigital Library
Index Terms
- Estimating Clickthrough Bias in the Cascade Model
Recommendations
Estimating Position Bias without Intrusive Interventions
WSDM '19: Proceedings of the Twelfth ACM International Conference on Web Search and Data MiningPresentation bias is one of the key challenges when learning from implicit feedback in search engines, as it confounds the relevance signal. While it was recently shown how counterfactual learning-to-rank (LTR) approaches \citeJoachims/etal/17a can ...
Offline Comparative Evaluation with Incremental, Minimally-Invasive Online Feedback
SIGIR '18: The 41st International ACM SIGIR Conference on Research & Development in Information RetrievalWe investigate the use of logged user interaction data---queries and clicks---for offline evaluation of new search systems in the context of counterfactual analysis. The challenge of evaluating a new ranker against log data collected from a static ...
Estimating Ad Clickthrough Rate through Query Intent Analysis
WI-IAT '09: Proceedings of the 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology - Volume 01Clickthrough rate, bid, and cost-per-click are known to be among the factors that impact the rank of an ad shown on a search result page. Search engines can benefit from estimating ad clickthrough in order to determine the quality of ads and maximize ...
Comments