{"id":"https://openalex.org/W3127028307","doi":"https://doi.org/10.5220/0010255108660873","title":"A New Benchmark for NLP in Social Sciences: Evaluating the Usefulness of Pre-trained Language Models for Classifying Open-ended Survey Responses","display_name":"A New Benchmark for NLP in Social Sciences: Evaluating the Usefulness of Pre-trained Language Models for Classifying Open-ended Survey Responses","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3127028307","doi":"https://doi.org/10.5220/0010255108660873","mag":"3127028307"},"language":"en","primary_location":{"id":"doi:10.5220/0010255108660873","doi":"https://doi.org/10.5220/0010255108660873","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010255108660873","pdf_url":null,"source":{"id":"https://openalex.org/S4363608837","display_name":"International Conference on Agents and Artificial Intelligence (ICAART)","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.5220/0010255108660873","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040862341","display_name":"Maximilian Meidinger","orcid":null,"observed_orcids":[]},"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":"Maximilian Meidinger","raw_affiliation_strings":["Department of Statistics, Ludwig-Maximilians-Universit\u00e4t, Munich, Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, Ludwig-Maximilians-Universit\u00e4t, Munich, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069469652","display_name":"Matthias A\u00dfenmacher","orcid":"https://orcid.org/0000-0003-2154-5774","observed_orcids":["https://orcid.org/0000-0003-2154-5774"]},"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":"Matthias A\u00dfenmacher","raw_affiliation_strings":["Department of Statistics, Ludwig-Maximilians-Universit\u00e4t, Munich, Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, Ludwig-Maximilians-Universit\u00e4t, Munich, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I8204097"],"apc_list":null,"apc_paid":null,"fwci":0.6931,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.7004595,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"866","last_page":"873"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.4860999882221222,"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":0.4860999882221222,"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":0.34299999475479126,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.09809999912977219,"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/benchmark-dataset","display_name":"benchmark dataset","score":0.7630000114440918},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"multi-label classification","score":0.8399999737739563},{"id":"https://openalex.org/keywords/open-ended-survey-responses","display_name":"open-ended survey responses","score":0.8429999947547913},{"id":"https://openalex.org/keywords/pre-trained-language-models","display_name":"pre-trained language models","score":0.8190000057220459},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.9710000157356262},{"id":"https://openalex.org/keywords/american-national-election-studies","display_name":"American National Election Studies","score":0.8389999866485596},{"id":"https://openalex.org/keywords/bert","display_name":"BERT","score":0.7919999957084656},{"id":"https://openalex.org/keywords/reproducibility","display_name":"reproducibility","score":0.8100000023841858}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.775131106376648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.750321626663208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6632257699966431},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.652267336845398},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4747213125228882},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0010255108660873","doi":"https://doi.org/10.5220/0010255108660873","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010255108660873","pdf_url":null,"source":{"id":"https://openalex.org/S4363608837","display_name":"International Conference on Agents and Artificial Intelligence (ICAART)","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:epub.ub.uni-muenchen.de:75923","doi":null,"is_oa":false,"landing_page_url":"https://epub.ub.uni-muenchen.de/75923/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401845","display_name":"Open access LMU (Ludwid Maxmilian's Universitat Munchen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I8204097","host_organization_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","host_organization_lineage":["https://openalex.org/I8204097"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:conferenceObject"}],"best_oa_location":{"id":"doi:10.5220/0010255108660873","doi":"https://doi.org/10.5220/0010255108660873","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010255108660873","pdf_url":null,"source":{"id":"https://openalex.org/S4363608837","display_name":"International Conference on Agents and Artificial Intelligence (ICAART)","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W54887220","https://openalex.org/W168564468","https://openalex.org/W1491576965","https://openalex.org/W1521626219","https://openalex.org/W1781770377","https://openalex.org/W1985865058","https://openalex.org/W2029517229","https://openalex.org/W2096974619","https://openalex.org/W2101234009","https://openalex.org/W2150102617","https://openalex.org/W2339380701","https://openalex.org/W2493916176","https://openalex.org/W2578535581","https://openalex.org/W2586665457","https://openalex.org/W2606964149","https://openalex.org/W2776751098","https://openalex.org/W2779050611","https://openalex.org/W2807815111","https://openalex.org/W2896457183","https://openalex.org/W2923014074","https://openalex.org/W2939507640","https://openalex.org/W2948740140","https://openalex.org/W2950813464","https://openalex.org/W2952272575","https://openalex.org/W2962711864","https://openalex.org/W2963310665","https://openalex.org/W2963341956","https://openalex.org/W2963748441","https://openalex.org/W2965373594","https://openalex.org/W2980282514","https://openalex.org/W2992422826","https://openalex.org/W3208594547","https://openalex.org/W4239160578","https://openalex.org/W4248524623"],"related_works":["https://openalex.org/W4393380037","https://openalex.org/W4391758695","https://openalex.org/W3112208384","https://openalex.org/W7160181373","https://openalex.org/W7166798307","https://openalex.org/W3215233766","https://openalex.org/W4410996875","https://openalex.org/W6992933520","https://openalex.org/W7030190435","https://openalex.org/W6922627353"],"abstract_inverted_index":{"In":[0],"order":[1],"to":[2,66,86,127],"evaluate":[3],"transfer":[4,160],"learning":[5,161],"models":[6,119,151],"for":[7,47,78,113,157],"Natural":[8],"Language":[9],"Processing":[10],"on":[11,52,120],"a":[12,74,93],"common":[13,75],"ground,":[14],"numerous":[15],"general":[16],"domain":[17],"(sets":[18],"of)":[19],"benchmark":[20,44,114],"data":[21,45,76,107,129,132],"sets":[22],"have":[23],"been":[24,56],"established":[25,159],"throughout":[26],"the":[27,32,59,100,121],"last":[28],"couple":[29],"of":[30,61,99,116,123,138,147],"years.Primarily,":[31],"proposed":[33,57],"tasks":[34],"are":[35],"classification":[36,50],"(binary,":[37],"multi-class),":[38],"regression":[39,150],"or":[40,141],"language":[41],"generation.However,":[42],"no":[43],"set":[46,77,133],"(extreme)":[48],"multi-label":[49,124],"relying":[51],"full-text":[53,135],"inputs":[54,136],"has":[55],"in":[58,81],"area":[60],"social":[62],"science":[63],"survey":[64],"research":[65],"this":[67,82],"date.This":[68],"constitutes":[69],"an":[70],"important":[71],"gap,":[72],"as":[73,152,154],"algorithm":[79],"development":[80],"field":[83],"could":[84],"lead":[85],"more":[87],"reproducible,":[88],"sustainable":[89],"research.Thus,":[90],"we":[91,143],"provide":[92,144],"transparent":[94],"and":[95],"fully":[96],"reproducible":[97],"preparation":[98],"2008":[101],"American":[102],"National":[103],"Election":[104],"Study":[105],"(ANES)":[106],"set,":[108],"which":[109],"can":[110],"be":[111],"used":[112],"comparisons":[115],"different":[117],"NLP":[118],"task":[122],"classification.In":[125],"contrast":[126],"other":[128],"sets,":[130],"our":[131],"comprises":[134],"instead":[137],"bag-of-words":[139],"representations":[140],"similar.Furthermore,":[142],"baseline":[145],"performances":[146],"simple":[148],"logistic":[149],"well":[153],"performance":[155],"values":[156],"recently":[158],"architectures,":[162],"namely":[163],"BERT":[164],"(":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-02-15T00:00:00"}