{"id":"https://openalex.org/W4411236296","doi":"https://doi.org/10.1145/3708319.3733685","title":"Simulating Human Opinions with Large Language Models","display_name":"Simulating Human Opinions with Large Language Models","publication_year":2025,"publication_date":"2025-06-12","ids":{"openalex":"https://openalex.org/W4411236296","doi":"https://doi.org/10.1145/3708319.3733685"},"language":"en","primary_location":{"id":"doi:10.1145/3708319.3733685","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3708319.3733685","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3708319.3733685","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3708319.3733685","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064098009","display_name":"Carolin Kaiser","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Carolin Kaiser","raw_affiliation_strings":["Nuremberg Institute for Market Decisions, Nuremberg, Germany"],"raw_orcid":"https://orcid.org/0009-0003-8563-8555","affiliations":[{"raw_affiliation_string":"Nuremberg Institute for Market Decisions, Nuremberg, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039989641","display_name":"Jakob Kaiser","orcid":"https://orcid.org/0000-0001-8205-1052"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jakob Kaiser","raw_affiliation_strings":["Nuremberg Institute for Market Decisions, Nuremberg, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8205-1052","affiliations":[{"raw_affiliation_string":"Nuremberg Institute for Market Decisions, Nuremberg, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000350188","display_name":"Vladimir Manewitsch","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vladimir Manewitsch","raw_affiliation_strings":["Nuremberg Institute for Market Decisions, Nuremberg, Germany"],"raw_orcid":"https://orcid.org/0009-0008-3100-1942","affiliations":[{"raw_affiliation_string":"Nuremberg Institute for Market Decisions, Nuremberg, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108900325","display_name":"Lea Rau","orcid":"https://orcid.org/0000-0003-0720-5909"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lea Rau","raw_affiliation_strings":["Ludwig-Maximilians-University, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0003-0720-5909","affiliations":[{"raw_affiliation_string":"Ludwig-Maximilians-University, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5117272995","display_name":"Rene Schallner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rene Schallner","raw_affiliation_strings":["Nuremberg Institute for Market Decisions, Nuremberg, Germany"],"raw_orcid":"https://orcid.org/0009-0008-8639-8940","affiliations":[{"raw_affiliation_string":"Nuremberg Institute for Market Decisions, Nuremberg, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5064098009"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.0395,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.98423996,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"82","last_page":"86"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9975000023841858,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9975000023841858,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9642000198364258,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.748023509979248},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3788281977176666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.748023509979248},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3788281977176666}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3708319.3733685","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3708319.3733685","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3708319.3733685","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3708319.3733685","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3708319.3733685","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3708319.3733685","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411236296.pdf","grobid_xml":"https://content.openalex.org/works/W4411236296.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2951249067","https://openalex.org/W3133702157","https://openalex.org/W3155346624","https://openalex.org/W4220993274","https://openalex.org/W4292947474","https://openalex.org/W4307475457","https://openalex.org/W4321455981","https://openalex.org/W4366549000","https://openalex.org/W4376117416","https://openalex.org/W4386567020","https://openalex.org/W4387305400","https://openalex.org/W4387378202","https://openalex.org/W4389984066","https://openalex.org/W4391713857","https://openalex.org/W4392716521","https://openalex.org/W4396608701","https://openalex.org/W4396833223","https://openalex.org/W4397011890","https://openalex.org/W4401389158","https://openalex.org/W4401448427","https://openalex.org/W4403578737","https://openalex.org/W4404569548","https://openalex.org/W4406588624"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Public":[0],"and":[1,11,19,64,104,123,139,147,160,173,209,224],"private":[2],"organizations":[3],"rely":[4],"on":[5,40,87,119],"opinion":[6,199,227],"surveys":[7,16],"to":[8,46,156,166,180],"inform":[9],"business":[10],"policy":[12],"decisions.":[13],"Yet,":[14],"empirical":[15,74],"are":[17],"costly":[18],"time-consuming.":[20],"Recent":[21],"advances":[22],"in":[23,31,135,205],"large":[24],"language":[25],"models":[26],"(LLMs)":[27],"have":[28],"sparked":[29],"interest":[30],"generating":[32],"synthetic":[33,69,125,172,192],"survey":[34,70],"data,":[35],"i.e.,":[36],"simulated":[37],"answers":[38],"based":[39,118],"target":[41],"demographics,":[42],"as":[43],"an":[44,73],"alternative":[45],"real":[47,167,174,212],"human":[48,56,112,137,213],"data.":[49,168],"But":[50],"how":[51],"well":[52],"can":[53],"LLMs":[54],"replicate":[55],"opinions?":[57],"In":[58],"this":[59],"ongoing":[60,220],"project,":[61],"we":[62,76,97],"develop":[63],"critically":[65],"evaluate":[66],"methods":[67],"for":[68,89,144,196,222],"sampling.":[71],"As":[72],"benchmark,":[75],"collected":[77],"responses":[78,126,138],"from":[79],"a":[80,90,107,115],"representative":[81],"U.S.":[82],"sample":[83],"(n":[84],"=":[85],"461)":[86],"preferences":[88],"common":[91],"consumer":[92],"good":[93],"(soft":[94],"drinks).":[95],"Then,":[96],"developed":[98],"ASPIRE":[99],"(Automated":[100],"Synthetic":[101,130],"Persona":[102],"Interview":[103],"Response":[105],"Engine),":[106],"tool":[108],"that":[109],"pairs":[110],"each":[111],"participant":[113],"with":[114],"\u201cdigital":[116],"twin\u201d":[117],"their":[120],"demographic":[121,188],"profile":[122],"generates":[124],"via":[127,229],"LLM":[128],"technology.":[129],"data":[131,152,175],"achieved":[132],"better-than-chance":[133],"accuracy":[134],"matching":[136],"approximated":[140],"aggregate":[141,198],"subjective":[142],"rankings":[143],"both":[145],"binary":[146],"Likert-scale":[148],"items.":[149],"However,":[150],"LLM-simulated":[151],"overestimated":[153],"humans\u2019":[154],"tendencies":[155],"provide":[157],"positive":[158],"ratings":[159],"exhibited":[161],"substantially":[162],"reduced":[163],"variance":[164],"compared":[165],"The":[169],"match":[170],"of":[171,211,218],"was":[176],"not":[177],"systematically":[178],"related":[179],"participants\u2019":[181],"age,":[182],"gender,":[183],"or":[184],"ethnicity,":[185],"indicating":[186],"no":[187],"bias.":[189],"Overall,":[190],"while":[191],"sampling":[193],"shows":[194],"promise":[195],"modeling":[197,228],"trends,":[200],"it":[201],"currently":[202],"falls":[203],"short":[204],"replicating":[206],"the":[207],"variability":[208],"complexity":[210],"opinions.":[214],"We":[215],"discuss":[216],"insights":[217],"our":[219],"project":[221],"accurate":[223],"responsible":[225],"user":[226],"LLMs.":[230]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}