Accurately interpreting clickthrough data as implicit feedback

by: Thorsten Joachims, Laura Granka, Bing Pan, Helene Hembrooke, Geri Gay

(2005), pp. 154-161.

View FullText article

ACM, DOI

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

suleehs, cleaner, MaineC, tolosoft, dartar, suripi, brusilovsky, rosta_farzan, dvallet, vitalaswp4, billsus, AlisonBabeu, chiapet, pprett, CMU-HCII (group), social_navigation (group), NETS-UAM (group), Adaptive-Web (group), avirr, abellogin, ChaTo

Find related articles with these CiteULike tags

authority, b, browsing, click, clicks, clickstream_data, clickthrough, clickthrough-data, clickthrough-history, click-tracking, evaluation, eye_tracking, eye-tracking, feedback, hci, implicit, implicit_feedback, implicit-feedback, implicit_ratings, implicit-relevance-feedback, information, information-retrieval, ir, ir-evaluation, linking, measure, personalization, preference, queries, ranking, relevance, retrieval, search, search-engines, search-ir-eval, search-log-analysis, search-logs, study, web, web_epistemology, web-mining

Abstract

This paper examines the reliability of implicit feedback generated from clickthrough data in WWW search. Analyzing the users' decision process using eyetracking and comparing implicit feedback against manual relevance judgments, we conclude that clicks are informative but biased. While this makes the interpretation of clicks as absolute relevance judgments difficult, we show that relative preferences derived from clicks are reasonably accurate on average.

@inproceedings{citeulike:379395, abstract = {This paper examines the reliability of implicit feedback generated from clickthrough data in WWW search. Analyzing the users' decision process using eyetracking and comparing implicit feedback against manual relevance judgments, we conclude that clicks are informative but biased. While this makes the interpretation of clicks as absolute relevance judgments difficult, we show that relative preferences derived from clicks are reasonably accurate on average.}, address = {New York, NY, USA}, author = {Joachims, Thorsten and Granka, Laura and Pan, Bing and Hembrooke, Helene and Gay, Geri }, booktitle = {SIGIR '05: Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval}, citeulike-article-id = {379395}, doi = {http://dx.doi.org/10.1145/1076034.1076063}, isbn = {1595930345}, keywords = {eye-tracking, implicit-feedback, information-retrieval}, pages = {154--161}, posted-at = {2007-02-03 00:25:44}, priority = {4}, publisher = {ACM Press}, title = {Accurately interpreting clickthrough data as implicit feedback}, url = {http://dx.doi.org/10.1145/1076034.1076063}, year = {2005} }

RIS record

TY - CONF ID - citeulike:379395 L3 - citeulike-article-id:379395 TI - Accurately interpreting clickthrough data as implicit feedback T2 - SIGIR '05: Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval SP - 154 EP - 161 AD - New York, NY, USA PB - ACM Press SN - 1595930345 N2 - This paper examines the reliability of implicit feedback generated from clickthrough data in WWW search. Analyzing the users' decision process using eyetracking and comparing implicit feedback against manual relevance judgments, we conclude that clicks are informative but biased. While this makes the interpretation of clicks as absolute relevance judgments difficult, we show that relative preferences derived from clicks are reasonably accurate on average. KW - eye-tracking KW - implicit-feedback KW - information-retrieval AU - Joachims, Thorsten AU - Granka, Laura AU - Pan, Bing AU - Hembrooke, Helene AU - Gay, Geri PY - 2005/// UR - http://dx.doi.org/10.1145/1076034.1076063 ER -

RIS BibTeX