{"id":"https://openalex.org/W3159789144","doi":"https://doi.org/10.1145/3446617","title":"RLPS: A Reinforcement Learning\u2013Based Framework for Personalized Search","display_name":"RLPS: A Reinforcement Learning\u2013Based Framework for Personalized Search","publication_year":2021,"publication_date":"2021-05-05","ids":{"openalex":"https://openalex.org/W3159789144","doi":"https://doi.org/10.1145/3446617","mag":"3159789144"},"language":"en","primary_location":{"id":"doi:10.1145/3446617","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3446617","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084847804","display_name":"Jing Yao","orcid":"https://orcid.org/0000-0002-0527-6095"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jing Yao","raw_affiliation_strings":["School of Information, Renmin University of China, Beijing, P. R China"],"affiliations":[{"raw_affiliation_string":"School of Information, Renmin University of China, Beijing, P. R China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010558184","display_name":"Zhicheng Dou","orcid":"https://orcid.org/0000-0002-9781-948X"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhicheng Dou","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, P. R China"],"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, P. R China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020766468","display_name":"Jun Xu","orcid":"https://orcid.org/0000-0001-7170-111X"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xu","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, P. R China"],"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, P. R China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025631695","display_name":"Ji-Rong Wen","orcid":"https://orcid.org/0000-0002-9777-9676"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I4210096250","display_name":"Beijing Institute of Big Data Research","ror":"https://ror.org/00s1sz824","country_code":"CN","type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I37796252","https://openalex.org/I4210096250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji-Rong Wen","raw_affiliation_strings":["Beijing Key Laboratory of Big Data Management and Analysis Methods, Key Laboratory of Data Engineering and Knowledge Engineering, Ministry of Education of the People\u2019s Republic of China","Beijing Key Laboratory of Big Data Management and Analysis Methods, Key Laboratory of Data Engineering and Knowledge Engineering, Ministry of Education of the People's Republic of China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Big Data Management and Analysis Methods, Key Laboratory of Data Engineering and Knowledge Engineering, Ministry of Education of the People\u2019s Republic of China","institution_ids":["https://openalex.org/I4210096250"]},{"raw_affiliation_string":"Beijing Key Laboratory of Big Data Management and Analysis Methods, Key Laboratory of Data Engineering and Knowledge Engineering, Ministry of Education of the People's Republic of China","institution_ids":["https://openalex.org/I1327237609"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5084847804"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":2.2032,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.8959272,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"39","issue":"3","first_page":"1","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9984999895095825,"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":0.996399998664856,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.9944000244140625,"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/computer-science","display_name":"Computer science","score":0.8428514003753662},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7761818766593933},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.7527058124542236},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7426897287368774},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6080527901649475},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5387685298919678},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.49349987506866455},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.4859570264816284},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4727645516395569},{"id":"https://openalex.org/keywords/personalized-search","display_name":"Personalized search","score":0.4270968437194824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42076507210731506},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4174690842628479},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3232659697532654},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.27640587091445923},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.17051973938941956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8428514003753662},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7761818766593933},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.7527058124542236},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7426897287368774},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6080527901649475},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5387685298919678},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.49349987506866455},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.4859570264816284},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4727645516395569},{"id":"https://openalex.org/C2776945383","wikidata":"https://www.wikidata.org/wiki/Q7170667","display_name":"Personalized search","level":3,"score":0.4270968437194824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42076507210731506},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4174690842628479},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3232659697532654},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.27640587091445923},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.17051973938941956},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3446617","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3446617","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6000000238418579}],"awards":[{"id":"https://openalex.org/G2217660864","display_name":null,"funder_award_id":"61872370, 61832017, 61872338","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7250361582","display_name":null,"funder_award_id":"2018YFC0830703","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1973435495","https://openalex.org/W1975409939","https://openalex.org/W1979809564","https://openalex.org/W1980617223","https://openalex.org/W1982858363","https://openalex.org/W1992549066","https://openalex.org/W1993378086","https://openalex.org/W2023599408","https://openalex.org/W2105059961","https://openalex.org/W2108279663","https://openalex.org/W2108862644","https://openalex.org/W2109677301","https://openalex.org/W2118286847","https://openalex.org/W2119717200","https://openalex.org/W2122654842","https://openalex.org/W2127799072","https://openalex.org/W2132314908","https://openalex.org/W2135500808","https://openalex.org/W2151049666","https://openalex.org/W2152314154","https://openalex.org/W2168717408","https://openalex.org/W2171392812","https://openalex.org/W2257117461","https://openalex.org/W2648699835","https://openalex.org/W2739916191","https://openalex.org/W2740384884","https://openalex.org/W2783640434","https://openalex.org/W2788295351","https://openalex.org/W2799544270","https://openalex.org/W2889658777","https://openalex.org/W2897050313","https://openalex.org/W2897055093","https://openalex.org/W2955887579","https://openalex.org/W2962770891","https://openalex.org/W2963561234","https://openalex.org/W3102778384","https://openalex.org/W3102899483","https://openalex.org/W3142239405","https://openalex.org/W4247950230","https://openalex.org/W4301113013"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W2116655434"],"abstract_inverted_index":{"Personalized":[0],"search":[1,8,28,38,67,76,90,101,124,150,241,252],"is":[2,69,80],"a":[3,41,70,99,127,135,204,216,255],"promising":[4],"way":[5],"to":[6,27,122,130,142,165,221],"improve":[7],"qualities":[9],"by":[10,202],"taking":[11],"user":[12,45,79,148,229],"interests":[13,84],"into":[14],"consideration.":[15],"Recently,":[16],"machine":[17],"learning":[18,21,121],"and":[19,47,78,109,125,149,152,181,189,207,254],"deep":[20],"techniques":[22],"have":[23,60],"been":[24,61],"successfully":[25],"applied":[26],"result":[29],"personalization.":[30],"Most":[31],"existing":[32,239],"models":[33,242],"simply":[34],"regard":[35],"the":[36,55,63,66,75,89,105,147,155,161,167,178,182,191,223,228,233,246,249],"personal":[37],"history":[39],"as":[40,131],"static":[42],"set":[43],"of":[44,72],"behaviors":[46],"learn":[48,166],"fixed":[49],"ranking":[50,112,158,192,219],"strategies":[51],"based":[52],"on":[53,248],"all":[54],"recorded":[56],"data.":[57],"Though":[58],"improvements":[59,237],"achieved,":[62],"essence":[64],"that":[65],"process":[68,108],"sequence":[71],"interactions":[73,145],"between":[74,146],"engine":[77],"ignored.":[81],"The":[82],"user\u2019s":[83,162,168,224],"may":[85],"dynamically":[86],"change":[87],"during":[88],"process,":[91],"therefore,":[92],"it":[93],"would":[94],"be":[95],"more":[96],"helpful":[97],"if":[98],"personalized":[100,123,157,218,240],"model":[102,159,193,200],"could":[103],"track":[104,143],"whole":[106],"interaction":[107],"adjust":[110],"its":[111],"strategy":[113],"continuously.":[114],"In":[115,211],"this":[116,172],"article,":[117],"we":[118,174,213],"adapt":[119],"reinforcement":[120],"propose":[126],"framework,":[128,173],"referred":[129],"RLPS.":[132],"It":[133],"utilizes":[134],"Markov":[136],"Decision":[137],"Process":[138],"(":[139],"MDP":[140],")":[141],"sequential":[144],"engine,":[151],"continuously":[153],"update":[154],"underlying":[156],"with":[160,187,194],"real-time":[163],"feedback":[164],"dynamic":[169],"interests.":[170],"Within":[171],"implement":[175],"two":[176],"models:":[177],"listwise":[179],"RLPS-L":[180,185],"hierarchical":[183],"RLPS-H.":[184],"interacts":[186],"users":[188],"trains":[190],"document":[195,209],"lists,":[196],"while":[197],"RLPS-H":[198],"improves":[199],"training":[201],"designing":[203],"layered":[205],"structure":[206],"introducing":[208],"pairs.":[210],"addition,":[212],"also":[214],"design":[215],"feedback-aware":[217],"component":[220],"capture":[222],"feedback,":[225],"which":[226],"impacts":[227],"interest":[230],"profile":[231],"for":[232],"next":[234],"query.":[235],"Significant":[236],"over":[238],"are":[243],"observed":[244],"in":[245],"experiments":[247],"public":[250],"AOL":[251],"log":[253],"commercial":[256],"log.":[257]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}