{"id":"https://openalex.org/W3156417005","doi":"https://doi.org/10.1145/3404835.3463228","title":"De-Biased Modeling of Search Click Behavior with Reinforcement Learning","display_name":"De-Biased Modeling of Search Click Behavior with Reinforcement Learning","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3156417005","doi":"https://doi.org/10.1145/3404835.3463228","mag":"3156417005"},"language":"en","primary_location":{"id":"doi:10.1145/3404835.3463228","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3463228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.10072","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jianghong Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jianghong Zhou","raw_affiliation_strings":["Emory University, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sayyed M. Zahiri","orcid":null},"institutions":[{"id":"https://openalex.org/I2799939184","display_name":"Home Depot (United States)","ror":"https://ror.org/031603425","country_code":"US","type":"company","lineage":["https://openalex.org/I2799939184"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sayyed M. Zahiri","raw_affiliation_strings":["The Home Depot, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Home Depot, Atlanta, GA, USA","institution_ids":["https://openalex.org/I2799939184"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Simon Hughes","orcid":null},"institutions":[{"id":"https://openalex.org/I2799939184","display_name":"Home Depot (United States)","ror":"https://ror.org/031603425","country_code":"US","type":"company","lineage":["https://openalex.org/I2799939184"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simon Hughes","raw_affiliation_strings":["The Home Depot, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Home Depot, Atlanta, GA, USA","institution_ids":["https://openalex.org/I2799939184"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Khalifeh Al Jadda","orcid":null},"institutions":[{"id":"https://openalex.org/I2799939184","display_name":"Home Depot (United States)","ror":"https://ror.org/031603425","country_code":"US","type":"company","lineage":["https://openalex.org/I2799939184"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khalifeh Al Jadda","raw_affiliation_strings":["The Home Depot, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Home Depot, Atlanta, GA, USA","institution_ids":["https://openalex.org/I2799939184"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Surya Kallumadi","orcid":null},"institutions":[{"id":"https://openalex.org/I2799939184","display_name":"Home Depot (United States)","ror":"https://ror.org/031603425","country_code":"US","type":"company","lineage":["https://openalex.org/I2799939184"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Surya Kallumadi","raw_affiliation_strings":["The Home Depot, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Home Depot, Atlanta, GA, USA","institution_ids":["https://openalex.org/I2799939184"]}]},{"author_position":"last","author":{"id":null,"display_name":"Eugene Agichtein","orcid":null},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Agichtein","raw_affiliation_strings":["Emory University, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150468666"],"apc_list":null,"apc_paid":null,"fwci":0.9787,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79774522,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1637","last_page":"1641"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7013000249862671},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6660000085830688},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.4657999873161316},{"id":"https://openalex.org/keywords/click-through-rate","display_name":"Click-through rate","score":0.42989999055862427},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4142000079154968},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.38429999351501465},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.37929999828338623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8015000224113464},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7013000249862671},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6660000085830688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6251999735832214},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6233999729156494},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.4657999873161316},{"id":"https://openalex.org/C115174607","wikidata":"https://www.wikidata.org/wiki/Q1100934","display_name":"Click-through rate","level":2,"score":0.42989999055862427},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4142000079154968},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38429999351501465},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3682999908924103},{"id":"https://openalex.org/C138744977","wikidata":"https://www.wikidata.org/wiki/Q5132438","display_name":"Clickstream","level":5,"score":0.35929998755455017},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31869998574256897},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3404835.3463228","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3463228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.10072","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.10072","pdf_url":"https://arxiv.org/pdf/2105.10072","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.10072","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.10072","pdf_url":"https://arxiv.org/pdf/2105.10072","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309381","display_name":"Emory University","ror":"https://ror.org/03czfpz43"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1976876561","https://openalex.org/W2007815473","https://openalex.org/W2026784708","https://openalex.org/W2099213975","https://openalex.org/W2106630408","https://openalex.org/W2113640060","https://openalex.org/W2154739689","https://openalex.org/W2339829457","https://openalex.org/W2507134384","https://openalex.org/W2553941291","https://openalex.org/W2905569957","https://openalex.org/W2997919341","https://openalex.org/W3012628147","https://openalex.org/W3093655911","https://openalex.org/W3094565211","https://openalex.org/W4249300810"],"related_works":[],"abstract_inverted_index":{"Users'":[0],"clicks":[1],"on":[2],"Web":[3,257],"search":[4,17,36,41,76,258],"results":[5],"are":[6,167],"one":[7],"of":[8,26,35,45,67,105,192,231],"the":[9,60,65,68,90,108,116,120,123,136,151,161,170,185,190,193,201,229,232,250],"key":[10],"signals":[11],"for":[12,39,100,173,252,255],"evaluating":[13],"and":[14,19,53,155,212,248],"improving":[15,256],"web":[16],"quality":[18],"have":[20,49,95],"been":[21,96],"widely":[22],"used":[23,168],"as":[24,86,169],"part":[25],"current":[27],"state-of-the-art":[28],"Learning-To-Rank(LTR)":[29],"models.":[30,56],"With":[31],"a":[32,75,179],"large":[33],"volume":[34],"logs":[37],"available":[38],"major":[40],"engines,":[42],"effective":[43],"models":[44,127],"searcher":[46],"click":[47,62,109,117,186,207,241],"behavior":[48,69,154],"emerged":[50],"to":[51,122,177,181,221,237,244],"evaluate":[52],"train":[54],"LTR":[55,125],"However,":[57],"when":[58,74],"modeling":[59,246],"users'":[61,152],"behavior,":[63],"considering":[64],"bias":[66,183,239],"is":[70,78,82],"imperative.":[71],"In":[72,131],"particular,":[73],"result":[77],"not":[79,83,87],"clicked,":[80],"it":[81],"necessarily":[84],"chosen":[85],"relevant":[88],"by":[89],"user,":[91],"but":[92],"instead":[93],"could":[94],"simply":[97],"missed,":[98],"especially":[99],"lower-ranked":[101],"results.":[102],"These":[103],"kinds":[104],"biases":[106],"in":[107,184,223,235,240],"log":[110],"data":[111],"can":[112],"be":[113],"incorporated":[114],"into":[115],"models,":[118],"propagating":[119],"errors":[121],"resulting":[124,156],"ranking":[126,224],"or":[128],"evaluation":[129],"metrics.":[130],"this":[132],"paper,":[133],"we":[134,196],"propose":[135],"De-biased":[137],"Reinforcement":[138],"Learning":[139],"Click":[140],"model":[141,145,234],"(DRLC).":[142],"The":[143],"DRLC":[144,162,194,218,233,254],"relaxes":[146],"previously":[147],"made":[148],"assumptions":[149],"about":[150],"examination":[153],"latent":[157],"states.":[158],"To":[159,188],"implement":[160],"model,":[163,195],"convolutional":[164],"neural":[165],"networks":[166,172],"value":[171],"reinforcement":[174],"learning,":[175],"trained":[176],"learn":[178],"policy":[180],"reduce":[182,238],"logs.":[187],"demonstrate":[189,228],"effectiveness":[191,230],"first":[197],"compare":[198],"performance":[199,247],"with":[200],"previous":[202],"state-of-art":[203],"approaches":[204],"using":[205,253],"established":[206],"prediction":[208],"metrics,":[209],"including":[210],"log-likelihood":[211],"perplexity.":[213],"We":[214],"further":[215],"show":[216],"that":[217],"also":[219],"leads":[220],"improvements":[222],"performance.":[225],"Our":[226],"experiments":[227],"learning":[236],"logs,":[242],"leading":[243],"improved":[245],"showing":[249],"potential":[251],"quality.":[259]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-23T08:51:43.019350","created_date":"2021-04-26T00:00:00"}