{"id":"https://openalex.org/W4410513106","doi":"https://doi.org/10.1145/3710947","title":"Collecting Qualitative Data at Scale with Large Language Models: A Case Study","display_name":"Collecting Qualitative Data at Scale with Large Language Models: A Case Study","publication_year":2025,"publication_date":"2025-05-02","ids":{"openalex":"https://openalex.org/W4410513106","doi":"https://doi.org/10.1145/3710947"},"language":"en","primary_location":{"id":"doi:10.1145/3710947","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3710947","pdf_url":null,"source":{"id":"https://openalex.org/S4210183893","display_name":"Proceedings of the ACM on Human-Computer Interaction","issn_l":"2573-0142","issn":["2573-0142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Human-Computer Interaction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3710947","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065305058","display_name":"Alejandro Cuevas","orcid":"https://orcid.org/0000-0001-6507-1334"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alejandro Cuevas","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041771110","display_name":"Jennifer V. Scurrell","orcid":"https://orcid.org/0000-0003-0404-9197"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jennifer V. Scurrell","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087896059","display_name":"Eva Maxfield Brown","orcid":"https://orcid.org/0000-0003-2564-0373"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eva M. Brown","raw_affiliation_strings":["University of Washington, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092912239","display_name":"Jason Entenmann","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Entenmann","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053319141","display_name":"Madeleine I. G. Daepp","orcid":"https://orcid.org/0000-0001-9689-2442"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Madeleine I. G. Daepp","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5065305058"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":13.6257,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.98483182,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"9","issue":"2","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"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/T12031","display_name":"Speech and dialogue systems","score":0.9817000031471252,"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/scale","display_name":"Scale (ratio)","score":0.5811710357666016},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5321649312973022},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.45690834522247314},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3646507263183594},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.2103506624698639},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.13257035613059998}],"concepts":[{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5811710357666016},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5321649312973022},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.45690834522247314},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3646507263183594},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.2103506624698639},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.13257035613059998}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3710947","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3710947","pdf_url":null,"source":{"id":"https://openalex.org/S4210183893","display_name":"Proceedings of the ACM on Human-Computer Interaction","issn_l":"2573-0142","issn":["2573-0142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Human-Computer Interaction","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3710947","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3710947","pdf_url":null,"source":{"id":"https://openalex.org/S4210183893","display_name":"Proceedings of the ACM on Human-Computer Interaction","issn_l":"2573-0142","issn":["2573-0142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Human-Computer Interaction","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W561751346","https://openalex.org/W1516534262","https://openalex.org/W1983467315","https://openalex.org/W1993269751","https://openalex.org/W2004538745","https://openalex.org/W2005597724","https://openalex.org/W2038572603","https://openalex.org/W2064296938","https://openalex.org/W2090138186","https://openalex.org/W2103879113","https://openalex.org/W2106991875","https://openalex.org/W2118882740","https://openalex.org/W2142758169","https://openalex.org/W2151814822","https://openalex.org/W2158242434","https://openalex.org/W2162961274","https://openalex.org/W2264742718","https://openalex.org/W2330516491","https://openalex.org/W2405187948","https://openalex.org/W2407300725","https://openalex.org/W2468750428","https://openalex.org/W2591974035","https://openalex.org/W2611556044","https://openalex.org/W2788016921","https://openalex.org/W2795783386","https://openalex.org/W2895844518","https://openalex.org/W2914188784","https://openalex.org/W2924196385","https://openalex.org/W2940530202","https://openalex.org/W2940884072","https://openalex.org/W2942367614","https://openalex.org/W2963903950","https://openalex.org/W3004984068","https://openalex.org/W3034879414","https://openalex.org/W3093956316","https://openalex.org/W3101528469","https://openalex.org/W3112421345","https://openalex.org/W3146973880","https://openalex.org/W3171850892","https://openalex.org/W3207553988","https://openalex.org/W4225115595","https://openalex.org/W4237017711","https://openalex.org/W4280554323","https://openalex.org/W4288080268","https://openalex.org/W4319165762","https://openalex.org/W4360978668","https://openalex.org/W4366003063","https://openalex.org/W4366547905","https://openalex.org/W4366548330","https://openalex.org/W4366549000","https://openalex.org/W4384662964","https://openalex.org/W4385693083","https://openalex.org/W4385984278","https://openalex.org/W4387547214","https://openalex.org/W4398143508","https://openalex.org/W4403422517"],"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":{"Chatbots":[0],"have":[1],"shown":[2],"promise":[3],"as":[4],"tools":[5],"to":[6,25,64,89,111,136],"scale":[7,83],"qualitative":[8,167],"data":[9],"collection.":[10],"Recent":[11],"advances":[12],"in":[13,75,148],"Large":[14],"Language":[15],"Models":[16],"(LLMs)":[17],"could":[18],"accelerate":[19],"this":[20,33],"process":[21],"by":[22,35],"allowing":[23],"researchers":[24],"easily":[26],"deploy":[27],"sophisticated":[28],"interviewing":[29],"chatbots.":[30],"We":[31,58,103,138],"test":[32],"assumption":[34],"conducting":[36],"a":[37,52,81,160],"large-scale":[38],"user":[39],"study":[40,158],"(n=399)":[41],"evaluating":[42,84,166],"3":[43],"different":[44],"chatbots,":[45],"two":[46],"of":[47,71,77,97,151],"which":[48,54,90],"are":[49],"LLM-based":[50],"and":[51,67,80,95,130,146,154,165],"baseline":[53],"employs":[55],"hard-coded":[56],"questions.":[57],"evaluate":[59],"the":[60,87,93,98,107,120,149],"results":[61],"with":[62,134,169],"respect":[63,135],"participant":[65],"engagement":[66],"experience,":[68],"established":[69,117],"metrics":[70],"chatbot":[72],"quality":[73,153],"grounded":[74],"theories":[76],"effective":[78],"communication,":[79],"novel":[82],"''richness''":[85],"or":[86,127],"extent":[88],"responses":[91,114,121],"capture":[92,123],"complexity":[94],"specificity":[96],"social":[99],"context":[100],"under":[101],"study.":[102],"find":[104,140],"that,":[105],"while":[106],"chatbots":[108],"were":[109],"able":[110],"elicit":[112],"high-quality":[113],"based":[115],"on":[116],"evaluation":[118],"metrics,":[119],"rarely":[122],"participants'":[124],"specific":[125],"motives":[126],"personalized":[128],"examples,":[129],"thus":[131],"perform":[132],"poorly":[133],"richness.":[137],"further":[139],"low":[141],"inter-rater":[142],"reliability":[143],"between":[144],"LLMs":[145],"humans":[147],"assessment":[150],"both":[152],"richness":[155],"metrics.":[156],"Our":[157],"offers":[159],"cautionary":[161],"tale":[162],"for":[163],"scaling":[164],"research":[168],"LLMs.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}