{"id":"https://openalex.org/W4367319056","doi":"https://doi.org/10.1145/3543873.3587623","title":"Psychotherapy AI Companion with Reinforcement Learning Recommendations and Interpretable Policy Dynamics","display_name":"Psychotherapy AI Companion with Reinforcement Learning Recommendations and Interpretable Policy Dynamics","publication_year":2023,"publication_date":"2023-04-28","ids":{"openalex":"https://openalex.org/W4367319056","doi":"https://doi.org/10.1145/3543873.3587623"},"language":"en","primary_location":{"id":"doi:10.1145/3543873.3587623","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543873.3587623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-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/A5018612055","display_name":"Baihan Lin","orcid":"https://orcid.org/0000-0002-7979-5509"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Baihan Lin","raw_affiliation_strings":["Columbia University, USA"],"affiliations":[{"raw_affiliation_string":"Columbia University, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065396462","display_name":"Guillermo Cecchi","orcid":"https://orcid.org/0000-0003-1013-8348"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guillermo Cecchi","raw_affiliation_strings":["IBM TJ Watson Research Center, USA"],"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055394860","display_name":"Djallel Bouneffouf","orcid":"https://orcid.org/0000-0003-3342-7513"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Djallel Bouneffouf","raw_affiliation_strings":["IBM TJ Watson Research Center, USA"],"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018612055"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":2.3581,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.8812804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"932","last_page":"939"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13283","display_name":"Mental Health Research Topics","score":0.9966999888420105,"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"}},"topics":[{"id":"https://openalex.org/T13283","display_name":"Mental Health Research Topics","score":0.9966999888420105,"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"}},{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9897000193595886,"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/T13234","display_name":"advanced mathematical theories","score":0.9764000177383423,"subfield":{"id":"https://openalex.org/subfields/2610","display_name":"Mathematical Physics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7935652136802673},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5882270336151123},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.5824956893920898},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47888320684432983},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.41347578167915344},{"id":"https://openalex.org/keywords/psychotherapist","display_name":"Psychotherapist","score":0.3906281590461731},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.33105364441871643},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.13204646110534668}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7935652136802673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5882270336151123},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.5824956893920898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47888320684432983},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.41347578167915344},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.3906281590461731},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.33105364441871643},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.13204646110534668},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3543873.3587623","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543873.3587623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1766812542","https://openalex.org/W2042281163","https://openalex.org/W2071133755","https://openalex.org/W2119762647","https://openalex.org/W2605350416","https://openalex.org/W2610906739","https://openalex.org/W2787933113","https://openalex.org/W2791681585","https://openalex.org/W2795199972","https://openalex.org/W2897623369","https://openalex.org/W2899457523","https://openalex.org/W2964044287","https://openalex.org/W2985355520","https://openalex.org/W2996959725","https://openalex.org/W3032916997","https://openalex.org/W3045464143","https://openalex.org/W3084167506","https://openalex.org/W3101063193","https://openalex.org/W3101707147","https://openalex.org/W4386363413","https://openalex.org/W4391043804"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"We":[0,40,63],"introduce":[1],"a":[2,108],"Reinforcement":[3,22],"Learning":[4,23],"Psychotherapy":[5],"AI":[6],"Companion":[7],"that":[8,65,84],"generates":[9],"topic":[10],"recommendations":[11],"for":[12,29],"therapists":[13],"based":[14],"on":[15,45,132],"patient":[16],"responses.":[17],"The":[18],"system":[19,67],"uses":[20],"Deep":[21],"(DRL)":[24],"to":[25,70],"generate":[26],"multi-objective":[27],"policies":[28,124],"four":[30],"different":[31,53,127,133],"psychiatric":[32],"conditions:":[33],"anxiety,":[34],"depression,":[35],"schizophrenia,":[36],"and":[37,61,83,92,114,130,145,157],"suicidal":[38],"cases.":[39],"present":[41],"our":[42],"experimental":[43],"results":[44],"the":[46,66,72,79,85,100,123,150],"accuracy":[47],"of":[48,55,152],"recommended":[49],"topics":[50,76],"using":[51],"three":[52],"scales":[54],"working":[56],"alliance":[57],"ratings:":[58],"task,":[59],"bond,":[60],"goal.":[62],"show":[64],"is":[68],"able":[69],"capture":[71],"real":[73],"data":[74],"(historical":[75],"discussed":[77],"by":[78,90],"therapists)":[80],"relatively":[81],"well,":[82],"best":[86],"performing":[87],"models":[88],"vary":[89],"disorder":[91],"rating":[93],"scale.":[94],"To":[95],"gain":[96],"interpretable":[97,146],"insights":[98],"into":[99],"learned":[101],"policies,":[102],"we":[103],"visualize":[104],"policy":[105,147],"trajectories":[106],"in":[107,122,139,154],"2D":[109],"principal":[110],"component":[111],"analysis":[112],"space":[113],"transition":[115],"matrices.":[116],"These":[117],"visualizations":[118],"reveal":[119],"distinct":[120],"patterns":[121],"trained":[125,131],"with":[126],"reward":[128],"signals":[129],"clinical":[134],"diagnoses.":[135],"Our":[136],"system\u2019s":[137],"success":[138],"generating":[140],"DIsorder-Specific":[141],"Multi-Objective":[142],"Policies":[143],"(DISMOP)":[144],"dynamics":[148],"demonstrates":[149],"potential":[151],"DRL":[153],"providing":[155],"personalized":[156],"efficient":[158],"therapeutic":[159],"recommendations.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}