{"id":"https://openalex.org/W4225873185","doi":"https://doi.org/10.1140/epjds/s13688-022-00353-7","title":"Evaluating the construct validity of text embeddings with application to survey questions","display_name":"Evaluating the construct validity of text embeddings with application to survey questions","publication_year":2022,"publication_date":"2022-07-07","ids":{"openalex":"https://openalex.org/W4225873185","doi":"https://doi.org/10.1140/epjds/s13688-022-00353-7"},"language":"en","primary_location":{"id":"doi:10.1140/epjds/s13688-022-00353-7","is_oa":true,"landing_page_url":"https://doi.org/10.1140/epjds/s13688-022-00353-7","pdf_url":"https://epjdatascience.springeropen.com/counter/pdf/10.1140/epjds/s13688-022-00353-7","source":{"id":"https://openalex.org/S2504380752","display_name":"EPJ Data Science","issn_l":"2193-1127","issn":["2193-1127"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EPJ Data Science","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://epjdatascience.springeropen.com/counter/pdf/10.1140/epjds/s13688-022-00353-7","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033588252","display_name":"Qixiang Fang","orcid":"https://orcid.org/0000-0003-2689-6653"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Qixiang Fang","raw_affiliation_strings":["Department of Methodology & Statistics, Utrecht University, Padualaan 14, Utrecht, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-2689-6653","affiliations":[{"raw_affiliation_string":"Department of Methodology & Statistics, Utrecht University, Padualaan 14, Utrecht, The Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004209770","display_name":"Dong Nguyen","orcid":"https://orcid.org/0000-0002-6062-3117"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Dong Nguyen","raw_affiliation_strings":["Department of Information & Computing Sciences, Utrecht University, Princetonplein 5, Utrecht, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information & Computing Sciences, Utrecht University, Princetonplein 5, Utrecht, The Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061913766","display_name":"Daniel L. Oberski","orcid":"https://orcid.org/0000-0001-7467-2297"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]},{"id":"https://openalex.org/I3018483916","display_name":"University Medical Center Utrecht","ror":"https://ror.org/0575yy874","country_code":"NL","type":"healthcare","lineage":["https://openalex.org/I3018483916"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Daniel L. Oberski","raw_affiliation_strings":["Department of Biostatistics and Data Science, Julius Center, University Medical Center Utrecht (UMCU), Universiteitsweg 100, Utrecht, The Netherlands","Department of Methodology & Statistics, Utrecht University, Padualaan 14, Utrecht, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics and Data Science, Julius Center, University Medical Center Utrecht (UMCU), Universiteitsweg 100, Utrecht, The Netherlands","institution_ids":["https://openalex.org/I3018483916"]},{"raw_affiliation_string":"Department of Methodology & Statistics, Utrecht University, Padualaan 14, Utrecht, The Netherlands","institution_ids":["https://openalex.org/I193662353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033588252"],"corresponding_institution_ids":["https://openalex.org/I193662353"],"apc_list":{"value":1190,"currency":"GBP","value_usd":1459},"apc_paid":{"value":1190,"currency":"GBP","value_usd":1459},"fwci":8.6332,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.97600897,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"11","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9887999892234802,"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"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9887999892234802,"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/T10557","display_name":"Social Media and Politics","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"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/T11239","display_name":"Social Capital and Networks","score":0.9835000038146973,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.7694709300994873},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.7126864194869995},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7065094709396362},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.689132571220398},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5985981822013855},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5247400403022766},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4638720750808716},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4459562301635742},{"id":"https://openalex.org/keywords/construct-validity","display_name":"Construct validity","score":0.42331716418266296},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41243240237236023},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34462136030197144},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3357601761817932},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15600302815437317},{"id":"https://openalex.org/keywords/psychometrics","display_name":"Psychometrics","score":0.11769020557403564},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.10936546325683594},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10282513499259949}],"concepts":[{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.7694709300994873},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.7126864194869995},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7065094709396362},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.689132571220398},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5985981822013855},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5247400403022766},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4638720750808716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4459562301635742},{"id":"https://openalex.org/C49453240","wikidata":"https://www.wikidata.org/wiki/Q1592163","display_name":"Construct validity","level":3,"score":0.42331716418266296},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41243240237236023},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34462136030197144},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3357601761817932},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15600302815437317},{"id":"https://openalex.org/C171606756","wikidata":"https://www.wikidata.org/wiki/Q506132","display_name":"Psychometrics","level":2,"score":0.11769020557403564},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.10936546325683594},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10282513499259949},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1140/epjds/s13688-022-00353-7","is_oa":true,"landing_page_url":"https://doi.org/10.1140/epjds/s13688-022-00353-7","pdf_url":"https://epjdatascience.springeropen.com/counter/pdf/10.1140/epjds/s13688-022-00353-7","source":{"id":"https://openalex.org/S2504380752","display_name":"EPJ Data Science","issn_l":"2193-1127","issn":["2193-1127"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EPJ Data Science","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2202.09166","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.09166","pdf_url":"https://arxiv.org/pdf/2202.09166","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:doaj.org/article:51d3035b9ea147ecad71e04b3e0b28f7","is_oa":true,"landing_page_url":"https://doaj.org/article/51d3035b9ea147ecad71e04b3e0b28f7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EPJ Data Science, Vol 11, Iss 1, Pp 1-31 (2022)","raw_type":"article"},{"id":"pmh:uu:oai:dspace.library.uu.nl:1874/425343","is_oa":true,"landing_page_url":"https://dspace.library.uu.nl/handle/1874/425343","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EPJ Data Science, 11(1), 1. Springer Open","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1140/epjds/s13688-022-00353-7","is_oa":true,"landing_page_url":"https://doi.org/10.1140/epjds/s13688-022-00353-7","pdf_url":"https://epjdatascience.springeropen.com/counter/pdf/10.1140/epjds/s13688-022-00353-7","source":{"id":"https://openalex.org/S2504380752","display_name":"EPJ Data Science","issn_l":"2193-1127","issn":["2193-1127"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EPJ Data Science","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8600000143051147,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G492894576","display_name":null,"funder_award_id":"Vidi.195.152","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G6221045140","display_name":"Advancing social science with valid measures derived from incidental data","funder_award_id":"VI.Vidi.195.152","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G7852550659","display_name":"Wht do u mean? Learning representations of social meaning for natural language processing","funder_award_id":"VI.Veni.192.130","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4225873185.pdf","grobid_xml":"https://content.openalex.org/works/W4225873185.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1847618513","https://openalex.org/W2135046866","https://openalex.org/W2171415274","https://openalex.org/W2321967967","https://openalex.org/W2345911458","https://openalex.org/W2493916176","https://openalex.org/W2496043434","https://openalex.org/W2514910268","https://openalex.org/W2604272474","https://openalex.org/W2769358515","https://openalex.org/W2787894218","https://openalex.org/W2799007037","https://openalex.org/W2799915114","https://openalex.org/W2882319491","https://openalex.org/W2891177506","https://openalex.org/W2893425640","https://openalex.org/W2896457183","https://openalex.org/W2906152891","https://openalex.org/W2911964244","https://openalex.org/W2945744671","https://openalex.org/W2963176474","https://openalex.org/W2963430224","https://openalex.org/W2963777125","https://openalex.org/W2970862333","https://openalex.org/W3009459039","https://openalex.org/W3015119146","https://openalex.org/W3023045752","https://openalex.org/W3035507081","https://openalex.org/W3080213414","https://openalex.org/W3083213769","https://openalex.org/W3105270635","https://openalex.org/W3118485687","https://openalex.org/W3202070718","https://openalex.org/W4233907442","https://openalex.org/W4238634189","https://openalex.org/W4239019441","https://openalex.org/W4391156274","https://openalex.org/W6945190599"],"related_works":["https://openalex.org/W4380136770","https://openalex.org/W2067674665","https://openalex.org/W4380568662","https://openalex.org/W3135512811","https://openalex.org/W2279151839","https://openalex.org/W2964200250","https://openalex.org/W2728743471","https://openalex.org/W2016749656","https://openalex.org/W2019962676","https://openalex.org/W2016506764"],"abstract_inverted_index":{"Abstract":[0],"Text":[1],"embedding":[2,122],"models":[3,25],"from":[4,62],"Natural":[5],"Language":[6],"Processing":[7],"can":[8,90],"map":[9],"text":[10,21,82,100,121],"data":[11],"(e.g.":[12],"words,":[13],"sentences,":[14],"documents)":[15],"to":[16,42,53,77,93,108],"meaningful":[17],"numerical":[18],"representations":[19,48],"(a.k.a.":[20],"embeddings).":[22],"While":[23],"such":[24],"are":[26,46],"increasingly":[27],"applied":[28],"in":[29],"social":[30],"science":[31],"research,":[32],"one":[33],"important":[34],"issue":[35],"is":[36],"often":[37],"not":[38],"addressed:":[39],"the":[40,50,69,72,79,94,114],"extent":[41],"which":[43],"these":[44],"embeddings":[45],"high-quality":[47],"of":[49,71,81,99,116],"information":[51],"needed":[52],"be":[54,91],"encoded.":[55],"We":[56],"view":[57],"this":[58,88],"quality":[59,80],"evaluation":[60],"problem":[61],"a":[63],"measurement":[64],"validity":[65,75,115],"perspective,":[66],"and":[67,96],"propose":[68],"use":[70],"classic":[73],"construct":[74],"framework":[76,89,107],"evaluate":[78],"embeddings.":[83,101],"First,":[84],"we":[85,103,112],"describe":[86],"how":[87],"adapted":[92,106],"opaque":[95],"high-dimensional":[97],"nature":[98],"Second,":[102],"apply":[104],"our":[105],"an":[109],"example":[110],"where":[111],"compare":[113],"survey":[117],"question":[118],"representation":[119],"across":[120],"models.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}