{"id":"https://openalex.org/W7161552795","doi":"https://doi.org/10.31449/inf.v50i13.13064","title":"Optimizing Long-Term User Engagement in Short-Video Recommendation via Reinforcement Learning: A Markov Decision Process Framework with Composite Rewards","display_name":"Optimizing Long-Term User Engagement in Short-Video Recommendation via Reinforcement Learning: A Markov Decision Process Framework with Composite Rewards","publication_year":2026,"publication_date":"2026-05-18","ids":{"openalex":"https://openalex.org/W7161552795","doi":"https://doi.org/10.31449/inf.v50i13.13064"},"language":null,"primary_location":{"id":"doi:10.31449/inf.v50i13.13064","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v50i13.13064","pdf_url":null,"source":{"id":"https://openalex.org/S4210173311","display_name":"Informatica","issn_l":"0350-5596","issn":["0350-5596","1854-3871"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310314525","host_organization_name":"Slovenian Society Informatika","host_organization_lineage":["https://openalex.org/P4310314525"],"host_organization_lineage_names":["Slovenian Society Informatika"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatica","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.31449/inf.v50i13.13064","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136435546","display_name":"Juan Di","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Juan Di","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5136435546"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.64781376,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"50","issue":"13","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.8877000212669373,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.8877000212669373,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.020600000396370888,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10667","display_name":"Emotion and Mood Recognition","score":0.010200000368058681,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8069000244140625},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7821999788284302},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.7605000138282776},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5619000196456909},{"id":"https://openalex.org/keywords/collaborative-filtering","display_name":"Collaborative filtering","score":0.5541999936103821},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.474700003862381},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4498000144958496},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.4293000102043152},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3822999894618988}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8069000244140625},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7821999788284302},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.7605000138282776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7351999878883362},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5619000196456909},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.5541999936103821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5304999947547913},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5194000005722046},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.474700003862381},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.4293000102043152},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3822999894618988},{"id":"https://openalex.org/C67712803","wikidata":"https://www.wikidata.org/wiki/Q7901853","display_name":"User modeling","level":3,"score":0.3662000000476837},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2955999970436096},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2612999975681305},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2606000006198883},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C2780150774","wikidata":"https://www.wikidata.org/wiki/Q252500","display_name":"User profile","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.31449/inf.v50i13.13064","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v50i13.13064","pdf_url":null,"source":{"id":"https://openalex.org/S4210173311","display_name":"Informatica","issn_l":"0350-5596","issn":["0350-5596","1854-3871"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310314525","host_organization_name":"Slovenian Society Informatika","host_organization_lineage":["https://openalex.org/P4310314525"],"host_organization_lineage_names":["Slovenian Society Informatika"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatica","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.31449/inf.v50i13.13064","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v50i13.13064","pdf_url":null,"source":{"id":"https://openalex.org/S4210173311","display_name":"Informatica","issn_l":"0350-5596","issn":["0350-5596","1854-3871"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310314525","host_organization_name":"Slovenian Society Informatika","host_organization_lineage":["https://openalex.org/P4310314525"],"host_organization_lineage_names":["Slovenian Society Informatika"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatica","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6427092552185059,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Under":[0],"the":[1,8,23,64,78,132,180],"dynamic":[2],"condition":[3],"of":[4,10,25,119,131,158],"short":[5,165],"video":[6,166],"platforms,":[7],"shortfall":[9],"conventional":[11],"recommendation":[12,48,66,167],"algorithms":[13],"that":[14,136],"pay":[15],"too":[16],"much":[17],"attention":[18],"to":[19,44,76,91,151],"short-term":[20,188],"indicators":[21],"at":[22],"cost":[24],"long-term":[26,83,112,192],"user":[27,79,84,193],"behavior":[28],"is":[29],"increasingly":[30],"obvious.":[31],"To":[32],"compensate":[33],"for":[34,144,163,179],"it,":[35],"we":[36],"utilized":[37],"a":[38,69,107,145,153,175],"Deep":[39],"Reinforcement":[40],"Learning":[41],"(DRL)":[42],"approach":[43],"develop":[45],"an":[46,117,128],"intelligent":[47],"system":[49],"framework":[50],"supported":[51],"by":[52,81],"deep":[53,99],"feature":[54],"engineering,":[55],"policy":[56],"updating,":[57],"and":[58,98,139,172],"online":[59],"interaction.":[60],"We":[61],"effectively":[62],"cast":[63],"difficult":[65],"process":[67],"into":[68],"Markov":[70],"Decision":[71],"Process":[72],"(MDP)":[73],"in":[74,123,149],"order":[75,150],"improve":[77],"experience":[80],"maximizing":[82,191],"value.":[85,194],"Experimental":[86],"findings":[87,157],"illustrate":[88],"that,":[89],"relative":[90],"baseline":[92],"models":[93],"like":[94],"collaborative":[95],"filtering":[96],"(MF)":[97],"neural":[100],"networks":[101],"(DNN),":[102],"our":[103],"DRL":[104],"agent":[105],"possesses":[106],"remarkable":[108],"lead":[109],"over":[110],"key":[111],"engagement":[113],"indicators,":[114],"specifically":[115],"gaining":[116],"improvement":[118],"more":[120],"than":[121],"22%":[122],"average":[124],"session":[125],"time.":[126],"Besides,":[127],"ablation":[129],"study":[130],"reward":[133,147],"function":[134],"confirmed":[135],"both":[137],"immediate":[138],"delayed":[140],"signals":[141],"are":[142],"necessary":[143],"composite":[146],"architecture":[148],"learn":[152],"good":[154],"policy.":[155],"The":[156],"this":[159],"work":[160],"have":[161],"repercussions":[162],"how":[164],"intelligence":[168],"can":[169],"be":[170],"boosted":[171],"even":[173],"indicate":[174],"new":[176],"research":[177],"path":[178],"recommender":[181],"systems":[182],"community,":[183],"shifting":[184],"away":[185],"from":[186],"using":[187],"metrics":[189],"towards":[190]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-05-19T00:00:00"}