{"id":"https://openalex.org/W4379986648","doi":"https://doi.org/10.1017/pan.2023.20","title":"Less Annotating, More Classifying: Addressing the Data Scarcity Issue of Supervised Machine Learning with Deep Transfer Learning and BERT-NLI","display_name":"Less Annotating, More Classifying: Addressing the Data Scarcity Issue of Supervised Machine Learning with Deep Transfer Learning and BERT-NLI","publication_year":2023,"publication_date":"2023-06-09","ids":{"openalex":"https://openalex.org/W4379986648","doi":"https://doi.org/10.1017/pan.2023.20"},"language":"en","primary_location":{"id":"doi:10.1017/pan.2023.20","doi":"https://doi.org/10.1017/pan.2023.20","is_oa":true,"landing_page_url":"https://doi.org/10.1017/pan.2023.20","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/05BB05555241762889825B080E097C27/S1047198723000207a.pdf/div-class-title-less-annotating-more-classifying-addressing-the-data-scarcity-issue-of-supervised-machine-learning-with-deep-transfer-learning-and-bert-nli-div.pdf","source":{"id":"https://openalex.org/S29331042","display_name":"Political Analysis","issn_l":"1047-1987","issn":["1047-1987","1476-4989"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","erih-plus","jufo-3","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Political Analysis","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/05BB05555241762889825B080E097C27/S1047198723000207a.pdf/div-class-title-less-annotating-more-classifying-addressing-the-data-scarcity-issue-of-supervised-machine-learning-with-deep-transfer-learning-and-bert-nli-div.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5098780938","display_name":"Moritz Laurer","orcid":"https://orcid.org/0000-0001-5781-162X","observed_orcids":["https://orcid.org/0000-0001-5781-162X"]},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Moritz Laurer","raw_affiliation_strings":["Department of Communication Science, Vrije Universiteit Amsterdam, Amsterdam, Netherlands. Email:"],"raw_orcid":"https://orcid.org/0000-0001-5781-162X","affiliations":[{"raw_affiliation_string":"Department of Communication Science, Vrije Universiteit Amsterdam, Amsterdam, Netherlands. Email:","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083395792","display_name":"Wouter van Atteveldt","orcid":"https://orcid.org/0000-0003-1237-538X","observed_orcids":["https://orcid.org/0000-0003-1237-538X"]},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Wouter van Atteveldt","raw_affiliation_strings":["Department of Communication Science, Vrije Universiteit Amsterdam, Amsterdam, Netherlands. Email:"],"raw_orcid":"https://orcid.org/0000-0003-1237-538X","affiliations":[{"raw_affiliation_string":"Department of Communication Science, Vrije Universiteit Amsterdam, Amsterdam, Netherlands. Email:","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023229681","display_name":"Andreu Casas","orcid":"https://orcid.org/0000-0001-6974-3652","observed_orcids":["https://orcid.org/0000-0001-6974-3652","https://orcid.org/0009-0004-8221-1270"]},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Andreu Casas","raw_affiliation_strings":["Department of Communication Science, Vrije Universiteit Amsterdam, Amsterdam, Netherlands. Email:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Communication Science, Vrije Universiteit Amsterdam, Amsterdam, Netherlands. Email:","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058382953","display_name":"Kasper Welbers","orcid":"https://orcid.org/0000-0003-2929-3815","observed_orcids":["https://orcid.org/0000-0003-2929-3815"]},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Kasper Welbers","raw_affiliation_strings":["Department of Communication Science, Vrije Universiteit Amsterdam, Amsterdam, Netherlands. Email:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Communication Science, Vrije Universiteit Amsterdam, Amsterdam, Netherlands. Email:","institution_ids":["https://openalex.org/I865915315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5098780938"],"corresponding_institution_ids":["https://openalex.org/I865915315"],"apc_list":{"value":3255,"currency":"USD","value_usd":3255},"apc_paid":{"value":3255,"currency":"USD","value_usd":3255},"fwci":54.0315,"has_fulltext":true,"cited_by_count":203,"citation_normalized_percentile":{"value":0.99841647,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"32","issue":"1","first_page":"84","last_page":"100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9282000064849854,"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":0.9282000064849854,"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/T10028","display_name":"Topic Modeling","score":0.047200001776218414,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.020099999383091927,"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/transfer-learning","display_name":"transfer learning","score":0.9490000009536743},{"id":"https://openalex.org/keywords/bert","display_name":"BERT","score":0.9150000214576721},{"id":"https://openalex.org/keywords/natural-language-inference","display_name":"natural language inference","score":0.9909999966621399},{"id":"https://openalex.org/keywords/data-scarcity","display_name":"data scarcity","score":0.7689999938011169},{"id":"https://openalex.org/keywords/annotation-effort","display_name":"annotation effort","score":0.4259999990463257},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.765999972820282},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.8709999918937683},{"id":"https://openalex.org/keywords/political-text-analysis","display_name":"political text analysis","score":0.8489999771118164},{"id":"https://openalex.org/keywords/language-models","display_name":"language models","score":0.5839999914169312},{"id":"https://openalex.org/keywords/political-science-research","display_name":"political science research","score":0.5049999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8189564943313599},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.7805638313293457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6821082234382629},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6582171320915222},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5086753964424133},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4928765296936035},{"id":"https://openalex.org/C2777673361","wikidata":"https://www.wikidata.org/wiki/Q5281228","display_name":"Disadvantage","level":2,"score":0.48554083704948425},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4553769528865814},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.4364573657512665},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.4206072688102722},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4174681305885315},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.07881948351860046},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1017/pan.2023.20","doi":"https://doi.org/10.1017/pan.2023.20","is_oa":true,"landing_page_url":"https://doi.org/10.1017/pan.2023.20","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/05BB05555241762889825B080E097C27/S1047198723000207a.pdf/div-class-title-less-annotating-more-classifying-addressing-the-data-scarcity-issue-of-supervised-machine-learning-with-deep-transfer-learning-and-bert-nli-div.pdf","source":{"id":"https://openalex.org/S29331042","display_name":"Political Analysis","issn_l":"1047-1987","issn":["1047-1987","1476-4989"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","erih-plus","jufo-3","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Political Analysis","raw_type":"journal-article"},{"id":"pmh:oai:research.vu.nl:openaire/d9649ca8-866b-41a2-8a42-1d6bfbc8f7f4","doi":null,"is_oa":true,"landing_page_url":"https://research.vu.nl/en/publications/d9649ca8-866b-41a2-8a42-1d6bfbc8f7f4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Laurer, M, Van Atteveldt, W, Casas, A & Welbers, K 2024, 'Less annotating, more classifying : Addressing the data scarcity issue of supervised machine learning with deep transfer learning and BERT-NLI', Political Analysis, vol. 32, no. 1, pp. 84-100. https://doi.org/10.1017/pan.2023.20","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:RePEc:cup:polals:v:32:y:2024:i:1:p:84-100_6","doi":null,"is_oa":false,"landing_page_url":"https://www.cambridge.org/core/product/identifier/S1047198723000207/type/journal_article","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"article"},{"id":"pmh:oai:share.osf.io:E0221-36F-160","doi":null,"is_oa":false,"landing_page_url":"http://osf.io/wqc86/","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":"","raw_type":"project"}],"best_oa_location":{"id":"doi:10.1017/pan.2023.20","doi":"https://doi.org/10.1017/pan.2023.20","is_oa":true,"landing_page_url":"https://doi.org/10.1017/pan.2023.20","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/05BB05555241762889825B080E097C27/S1047198723000207a.pdf/div-class-title-less-annotating-more-classifying-addressing-the-data-scarcity-issue-of-supervised-machine-learning-with-deep-transfer-learning-and-bert-nli-div.pdf","source":{"id":"https://openalex.org/S29331042","display_name":"Political Analysis","issn_l":"1047-1987","issn":["1047-1987","1476-4989"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","erih-plus","jufo-3","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Political Analysis","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1000966202","display_name":null,"funder_award_id":"EINF-3006","funder_id":"https://openalex.org/F4320311215","funder_display_name":"Heinrich B\u00f6ll Stiftung"},{"id":"https://openalex.org/G7129838843","display_name":null,"funder_award_id":"EINF-3006","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320311215","display_name":"Heinrich B\u00f6ll Stiftung","ror":"https://ror.org/01vneh441"},{"id":"https://openalex.org/F4320321014","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4379986648.pdf","grobid_xml":"https://content.openalex.org/works/W4379986648.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1908686216","https://openalex.org/W2010455623","https://openalex.org/W2095655043","https://openalex.org/W2101234009","https://openalex.org/W2159544539","https://openalex.org/W2165698076","https://openalex.org/W2170890002","https://openalex.org/W2250539671","https://openalex.org/W2515855575","https://openalex.org/W2604272474","https://openalex.org/W2607892599","https://openalex.org/W2626778328","https://openalex.org/W2753354158","https://openalex.org/W2798812533","https://openalex.org/W2900657986","https://openalex.org/W2962802560","https://openalex.org/W2963341956","https://openalex.org/W2970200208","https://openalex.org/W2979736514","https://openalex.org/W2979826702","https://openalex.org/W3002104146","https://openalex.org/W3020745670","https://openalex.org/W3022247203","https://openalex.org/W3023365807","https://openalex.org/W3030163527","https://openalex.org/W3032388710","https://openalex.org/W3034824379","https://openalex.org/W3036188798","https://openalex.org/W3124636409","https://openalex.org/W3125733373","https://openalex.org/W3157374291","https://openalex.org/W3159574466","https://openalex.org/W3168278108","https://openalex.org/W3211686893","https://openalex.org/W4200425490","https://openalex.org/W4224295605","https://openalex.org/W4283688409","https://openalex.org/W4318067207","https://openalex.org/W4398652062","https://openalex.org/W6907845515","https://openalex.org/W6949549905"],"related_works":["https://openalex.org/W3112208384","https://openalex.org/W7067130495","https://openalex.org/W4387623590","https://openalex.org/W4323349213","https://openalex.org/W4386852459","https://openalex.org/W4226249120","https://openalex.org/W4406376809","https://openalex.org/W6990225172","https://openalex.org/W4417317892","https://openalex.org/W3127028307"],"abstract_inverted_index":{"Abstract":[0],"Supervised":[1],"machine":[2,20],"learning":[3,21,67,118,179,193],"is":[4,22,35],"an":[5],"increasingly":[6],"popular":[7],"tool":[8],"for":[9,25,51,199],"analyzing":[10],"large":[11],"political":[12,200],"text":[13],"corpora.":[14],"The":[15],"main":[16],"disadvantage":[17],"of":[18,27,116,123,191],"supervised":[19],"the":[23,39,57,114],"need":[24],"thousands":[26],"manually":[28],"annotated":[29],"training":[30,49,101],"data":[31,50,96],"points.":[32],"This":[33,61],"issue":[34],"particularly":[36,181],"important":[37],"in":[38,77],"social":[40],"sciences":[41],"where":[42],"most":[43],"new":[44,48,53,197],"research":[45,59],"questions":[46],"require":[47],"a":[52,120],"task":[54],"tailored":[55],"to":[56,136,143],"specific":[58],"question.":[60],"paper":[62],"analyses":[63],"how":[64],"deep":[65],"transfer":[66,117,152,178,192],"can":[68,83,97],"help":[69],"address":[70],"this":[71],"challenge":[72],"by":[73,100,188,195],"accumulating":[74],"\u201cprior":[75],"knowledge\u201d":[76],"language":[78,86,107],"models.":[79],"Models":[80],"like":[81,105],"BERT":[82],"learn":[84],"statistical":[85],"patterns":[87],"through":[88],"pre-training":[89],"(\u201clanguage":[90],"knowledge\u201d),":[91],"and":[92,194],"reliance":[93],"on":[94,102,119,134,140,160,170,183],"task-specific":[95],"be":[98],"reduced":[99],"universal":[103],"tasks":[104],"natural":[106],"inference":[108],"(NLI;":[109],"\u201ctask":[110],"knowledge\u201d).":[111],"We":[112,186],"demonstrate":[113],"benefits":[115],"wide":[121],"range":[122],"eight":[124,128],"tasks.":[125],"Across":[126],"these":[127],"tasks,":[129],"our":[130],"BERT-NLI":[131,158],"model":[132],"fine-tuned":[133,159],"100":[135],"2,500":[137],"texts":[138,162],"performs":[139],"average":[141],"10.7":[142],"18.3":[144],"percentage":[145],"points":[146],"better":[147],"than":[148],"classical":[149,167],"models":[150,168],"without":[151],"learning.":[153],"Our":[154],"study":[155],"indicates":[156],"that":[157,177],"500":[161],"achieves":[163],"similar":[164],"performance":[165],"as":[166],"trained":[169],"around":[171],"5,000":[172],"texts.":[173],"Moreover,":[174],"we":[175],"show":[176],"works":[180],"well":[182],"imbalanced":[184],"data.":[185],"conclude":[187],"discussing":[189],"limitations":[190],"outlining":[196],"opportunities":[198],"science":[201],"research.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":77},{"year":2025,"cited_by_count":64},{"year":2024,"cited_by_count":42},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-06-10T00:00:00"}