{"id":"https://openalex.org/W7208816749","doi":"https://doi.org/10.1145/3800935.3830835","title":"\u201cHalf My Survey Data Is Bad; The Problem Is, I Can't Tell Which Half\u201d: Evaluating the Validatability of Large-Scale Survey Data Using 176 Algorithmically Generated Personas","display_name":"\u201cHalf My Survey Data Is Bad; The Problem Is, I Can't Tell Which Half\u201d: Evaluating the Validatability of Large-Scale Survey Data Using 176 Algorithmically Generated Personas","publication_year":2026,"publication_date":"2026-09-05","ids":{"openalex":"https://openalex.org/W7208816749","doi":"https://doi.org/10.1145/3800935.3830835"},"language":"en","primary_location":{"id":"doi:10.1145/3800935.3830835","doi":"https://doi.org/10.1145/3800935.3830835","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3800935.3830835","pdf_url":null,"source":{"id":"https://openalex.org/S7407088164","display_name":"ACM Conference on Hypertext and Social Media (HT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 37th ACM Conference on Hypertext","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3800935.3830835","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044849571","display_name":"Bernard J. Jim Jansen","orcid":"https://orcid.org/0000-0002-6468-6609","observed_orcids":["https://orcid.org/0000-0002-6468-6609"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bernard J. Jansen","raw_affiliation_strings":["Peking University, Department of Information Management, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6468-6609","affiliations":[{"raw_affiliation_string":"Peking University, Department of Information Management, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150386530","display_name":"Marwan Akari","orcid":"https://orcid.org/0000-0002-1883-0315","observed_orcids":["https://orcid.org/0000-0002-1883-0315"]},"institutions":[{"id":"https://openalex.org/I92528248","display_name":"Qatar Foundation","ror":"https://ror.org/01cawbq05","country_code":"QA","type":"funder","lineage":["https://openalex.org/I92528248"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Marwan Akari","raw_affiliation_strings":["Qatar Foundation, Doha, Qatar"],"raw_orcid":"https://orcid.org/0000-0002-1883-0315","affiliations":[{"raw_affiliation_string":"Qatar Foundation, Doha, Qatar","institution_ids":["https://openalex.org/I92528248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055381416","display_name":"S. Rezai Amin","orcid":"https://orcid.org/0009-0000-9414-4002","observed_orcids":["https://orcid.org/0009-0000-9414-4002"]},"institutions":[{"id":"https://openalex.org/I4210089979","display_name":"Carnegie Mellon University Qatar","ror":"https://ror.org/00az5dt38","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210089979","https://openalex.org/I74973139"]},{"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":["QA","US"],"is_corresponding":false,"raw_author_name":"Safa Amin","raw_affiliation_strings":["Carnegie Mellon University in Qatar, Doha, Qatar"],"raw_orcid":"https://orcid.org/0009-0000-9414-4002","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University in Qatar, Doha, Qatar","institution_ids":["https://openalex.org/I4210089979","https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112865214","display_name":"Soon\u2010gyo Jung","orcid":"https://orcid.org/0000-0002-6130-8012","observed_orcids":["https://orcid.org/0000-0002-6130-8012"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soon-Gyo Jung","raw_affiliation_strings":["Qatar Computing Research Institute, Doha, Qatar"],"raw_orcid":"https://orcid.org/0000-0002-6130-8012","affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Doha, Qatar","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121963824","display_name":"Danial Amin","orcid":"https://orcid.org/0009-0000-7597-2267","observed_orcids":["https://orcid.org/0009-0000-7597-2267"]},"institutions":[{"id":"https://openalex.org/I79765343","display_name":"University of Vaasa","ror":"https://ror.org/03769b225","country_code":"FI","type":"education","lineage":["https://openalex.org/I79765343"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Danial Amin","raw_affiliation_strings":["University of Vaasa, School of Marketing and Communication, Vaasa, Finland"],"raw_orcid":"https://orcid.org/0009-0000-7597-2267","affiliations":[{"raw_affiliation_string":"University of Vaasa, School of Marketing and Communication, Vaasa, Finland","institution_ids":["https://openalex.org/I79765343"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083126896","display_name":"Joni O. Salminen","orcid":"https://orcid.org/0000-0003-3230-0561","observed_orcids":["https://orcid.org/0000-0003-3230-0561"]},"institutions":[{"id":"https://openalex.org/I79765343","display_name":"University of Vaasa","ror":"https://ror.org/03769b225","country_code":"FI","type":"education","lineage":["https://openalex.org/I79765343"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Joni Salminen","raw_affiliation_strings":["University of Vaasa, School of Marketing and Communication, Vaasa, Finland"],"raw_orcid":"https://orcid.org/0000-0003-3230-0561","affiliations":[{"raw_affiliation_string":"University of Vaasa, School of Marketing and Communication, Vaasa, Finland","institution_ids":["https://openalex.org/I79765343"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62042735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"368","last_page":"377"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11539","display_name":"Survey Methodology and Nonresponse","score":0.9721999764442444,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11539","display_name":"Survey Methodology and Nonresponse","score":0.9721999764442444,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"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/T14074","display_name":"Persona Design and Applications","score":0.015699999406933784,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.005400000140070915,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/survey-data-validity","display_name":"survey data validity","score":0.925000011920929},{"id":"https://openalex.org/keywords/attention-checks","display_name":"attention checks","score":0.7929999828338623},{"id":"https://openalex.org/keywords/personas","display_name":"personas","score":0.7670000195503235},{"id":"https://openalex.org/keywords/data-quality","display_name":"data quality","score":0.6790000200271606},{"id":"https://openalex.org/keywords/social-media-users","display_name":"social media users","score":0.7599999904632568},{"id":"https://openalex.org/keywords/persona-generation","display_name":"persona generation","score":0.37400001287460327}],"concepts":[{"id":"https://openalex.org/C313442","wikidata":"https://www.wikidata.org/wiki/Q778556","display_name":"Persona","level":2,"score":0.8460999727249146},{"id":"https://openalex.org/C198477413","wikidata":"https://www.wikidata.org/wiki/Q7647069","display_name":"Survey data collection","level":2,"score":0.7699000239372253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5916000008583069},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5295000076293945},{"id":"https://openalex.org/C2780224610","wikidata":"https://www.wikidata.org/wiki/Q1530061","display_name":"Credibility","level":2,"score":0.5238000154495239},{"id":"https://openalex.org/C73945780","wikidata":"https://www.wikidata.org/wiki/Q814232","display_name":"Survey methodology","level":2,"score":0.5171999931335449},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5083000063896179},{"id":"https://openalex.org/C173481278","wikidata":"https://www.wikidata.org/wiki/Q7257997","display_name":"Survey research","level":2,"score":0.5009999871253967},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.48570001125335693},{"id":"https://openalex.org/C146804397","wikidata":"https://www.wikidata.org/wiki/Q4118918","display_name":"General Social Survey","level":2,"score":0.4056999981403351},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C2778023277","wikidata":"https://www.wikidata.org/wiki/Q321703","display_name":"Premise","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3617999851703644},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3490000069141388},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C2780084366","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demographics","level":2,"score":0.3393999934196472},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.28949999809265137},{"id":"https://openalex.org/C5733905","wikidata":"https://www.wikidata.org/wiki/Q10744315","display_name":"Survey sampling","level":3,"score":0.2759000062942505},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2728999853134155},{"id":"https://openalex.org/C2780977526","wikidata":"https://www.wikidata.org/wiki/Q42417149","display_name":"Data exploration","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C2989497712","wikidata":"https://www.wikidata.org/wiki/Q7647069","display_name":"Web survey","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3800935.3830835","doi":"https://doi.org/10.1145/3800935.3830835","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3800935.3830835","pdf_url":null,"source":{"id":"https://openalex.org/S7407088164","display_name":"ACM Conference on Hypertext and Social Media (HT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 37th ACM Conference on Hypertext","raw_type":"proceedings-article"},{"id":"pmh:oai:osuva.uwasa.fi:11111/21325","doi":null,"is_oa":true,"landing_page_url":"https://osuva.uwasa.fi/handle/11111/21325","pdf_url":"https://osuva.uwasa.fi/bitstreams/77cf6676-f69c-499f-9d59-540c54dd5cc9/download","source":{"id":"https://openalex.org/S4306400974","display_name":"Osuva (University of Vaasa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I79765343","host_organization_name":"University of Vaasa","host_organization_lineage":["https://openalex.org/I79765343"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SoleCRIS","raw_type":"article"},{"id":"pmh:oai:share.osf.io:dfd04fec-478b-4ffe-874f-31245b92d825","doi":null,"is_oa":false,"landing_page_url":"https://osf.io/en3gj","pdf_url":null,"source":{"id":"https://openalex.org/S4306401127","display_name":"OSF Preprints (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Project"}],"best_oa_location":{"id":"doi:10.1145/3800935.3830835","doi":"https://doi.org/10.1145/3800935.3830835","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3800935.3830835","pdf_url":null,"source":{"id":"https://openalex.org/S7407088164","display_name":"ACM Conference on Hypertext and Social Media (HT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 37th ACM Conference on Hypertext","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[{"id":"https://openalex.org/study-designs/observational-study","display_name":"Observational Study"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7208816749.pdf","grobid_xml":"https://content.openalex.org/works/W7208816749.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W16527307","https://openalex.org/W1046275439","https://openalex.org/W1603922146","https://openalex.org/W1877093828","https://openalex.org/W2010398643","https://openalex.org/W2015375844","https://openalex.org/W2015629112","https://openalex.org/W2028045345","https://openalex.org/W2035833221","https://openalex.org/W2097235580","https://openalex.org/W2116323796","https://openalex.org/W2118030335","https://openalex.org/W2125076921","https://openalex.org/W2137972841","https://openalex.org/W2138801599","https://openalex.org/W2146436037","https://openalex.org/W2152209726","https://openalex.org/W2152427206","https://openalex.org/W2327620174","https://openalex.org/W2803499031","https://openalex.org/W2804752982","https://openalex.org/W2898706124","https://openalex.org/W2964352131","https://openalex.org/W3032424578","https://openalex.org/W3032525876","https://openalex.org/W3091443127","https://openalex.org/W3094678127","https://openalex.org/W3155511510","https://openalex.org/W4220889860","https://openalex.org/W4226251359","https://openalex.org/W4291667741","https://openalex.org/W4297156445","https://openalex.org/W4298009453","https://openalex.org/W4298143500","https://openalex.org/W4311557029","https://openalex.org/W4367179765","https://openalex.org/W4380985699","https://openalex.org/W4386128600","https://openalex.org/W4386546094","https://openalex.org/W4387150449","https://openalex.org/W4392548249","https://openalex.org/W4392863756","https://openalex.org/W4395691274","https://openalex.org/W4399203182","https://openalex.org/W4411236296","https://openalex.org/W7133358946"],"related_works":["https://openalex.org/W7169748651","https://openalex.org/W7213255141","https://openalex.org/W7203462600","https://openalex.org/W4416424397","https://openalex.org/W7220710590","https://openalex.org/W4284683829","https://openalex.org/W4407357306","https://openalex.org/W4254640198","https://openalex.org/W7204765136","https://openalex.org/W4388430701"],"abstract_inverted_index":{"Survey":[0],"data":[1,17,41,132,174,193,197],"is":[2,18,26,51],"foundational":[3],"to":[4,183],"much":[5],"user":[6],"research,":[7],"including":[8],"design":[9],"artifacts":[10,190],"such":[11,47,192],"as":[12,48,71,81,86],"personas.":[13],"However,":[14],"if":[15],"survey":[16,40,45,59,161,173,207],"invalidatable,":[19],"the":[20,33,160,184,201],"credibility":[21],"of":[22,60,109,122,149,151,159,203],"any":[23],"downstream":[24],"analysis":[25],"fundamentally":[27],"undermined.":[28],"This":[29],"work":[30],"starts":[31],"with":[32,104,141],"premise":[34],"that":[35,171,189],"distinguishing":[36],"valid":[37,83],"from":[38],"invalid":[39,87],"solely":[42,205],"through":[43,178],"internal":[44,179],"checks,":[46,50],"attention":[49,93],"practically":[52],"infeasible.":[53],"We":[54,95],"conducted":[55],"a":[56,120],"large-scale":[57,172],"empirical":[58],"social":[61],"media":[62],"users":[63],"(N":[64],"\u2248":[65],"20,000)":[66],"and":[67,84,124,188],"used":[68],"persona":[69,152],"creation":[70],"an":[72,147],"analytical":[73],"lens.":[74],"Of":[75],"these":[76],"responses,":[77],"8,140":[78],"were":[79,129,154],"classified":[80],"(ostensibly)":[82],"11,860":[85],"based":[88],"on":[89,206],"passing":[90],"or":[91],"failing":[92],"checks.":[94],"construct":[96],"ten":[97],"datasets":[98],"by":[99],"progressively":[100],"replacing":[101],"\u2018valid\u2019":[102],"responses":[103],"\u2018invalid\u2019":[105],"ones":[106],"in":[107,119,138,191],"increments":[108],"10%.":[110],"From":[111],"each":[112],"dataset,":[113],"we":[114],"generate":[115],"16":[116],"personas,":[117],"resulting":[118],"total":[121],"176,":[123],"compare":[125],"their":[126],"divergence.":[127],"Results":[128],"stable":[130],"despite":[131],"degradation.":[133],"Persona":[134],"demographics":[135],"remained":[136],"unchanged":[137],"most":[139],"conditions,":[140],"demographic":[142],"consistency":[143],"at":[144],"nearly":[145],"90%;":[146],"average":[148],"12%":[150],"attributes":[153],"unchanged.":[155],"More":[156],"than":[157],"80%":[158],"item":[162],"diversity":[163],"was":[164],"consistent":[165],"across":[166],"datasets.":[167],"The":[168],"findings":[169],"are":[170],"may":[175],"be":[176],"unverifiable":[177],"checks":[180],"alone":[181],"due":[182],"Validity":[185],"Masking":[186],"Effect,":[187],"can":[194],"obscure":[195],"underlying":[196],"quality":[198],"issues,":[199],"highlighting":[200],"risks":[202],"relying":[204],"data.":[208]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-09-06T00:00:00"}