{"id":"https://openalex.org/W4313127206","doi":"https://doi.org/10.1145/3558100.3563855","title":"Theory entity extraction for social and behavioral sciences papers using distant supervision","display_name":"Theory entity extraction for social and behavioral sciences papers using distant supervision","publication_year":2022,"publication_date":"2022-09-20","ids":{"openalex":"https://openalex.org/W4313127206","doi":"https://doi.org/10.1145/3558100.3563855"},"language":"en","primary_location":{"id":"doi:10.1145/3558100.3563855","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3558100.3563855","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3558100.3563855","source":null,"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 22nd ACM Symposium on Document Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3558100.3563855","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101515728","display_name":"Xin Wei","orcid":"https://orcid.org/0009-0000-0247-0469"},"institutions":[{"id":"https://openalex.org/I4210092569","display_name":"Dominion University College","ror":"https://ror.org/003kqe171","country_code":"GH","type":"education","lineage":["https://openalex.org/I4210092569"]},{"id":"https://openalex.org/I81365321","display_name":"Old Dominion University","ror":"https://ror.org/04zjtrb98","country_code":"US","type":"education","lineage":["https://openalex.org/I81365321"]}],"countries":["GH","US"],"is_corresponding":true,"raw_author_name":"Xin Wei","raw_affiliation_strings":["Old Dominion University"],"affiliations":[{"raw_affiliation_string":"Old Dominion University","institution_ids":["https://openalex.org/I4210092569","https://openalex.org/I81365321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054690853","display_name":"Lamia Salsabil","orcid":"https://orcid.org/0000-0002-6162-2896"},"institutions":[{"id":"https://openalex.org/I4210092569","display_name":"Dominion University College","ror":"https://ror.org/003kqe171","country_code":"GH","type":"education","lineage":["https://openalex.org/I4210092569"]},{"id":"https://openalex.org/I81365321","display_name":"Old Dominion University","ror":"https://ror.org/04zjtrb98","country_code":"US","type":"education","lineage":["https://openalex.org/I81365321"]}],"countries":["GH","US"],"is_corresponding":false,"raw_author_name":"Lamia Salsabil","raw_affiliation_strings":["Old Dominion University"],"affiliations":[{"raw_affiliation_string":"Old Dominion University","institution_ids":["https://openalex.org/I4210092569","https://openalex.org/I81365321"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075242841","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0003-0173-4463"},"institutions":[{"id":"https://openalex.org/I4210092569","display_name":"Dominion University College","ror":"https://ror.org/003kqe171","country_code":"GH","type":"education","lineage":["https://openalex.org/I4210092569"]},{"id":"https://openalex.org/I81365321","display_name":"Old Dominion University","ror":"https://ror.org/04zjtrb98","country_code":"US","type":"education","lineage":["https://openalex.org/I81365321"]}],"countries":["GH","US"],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":["Old Dominion University"],"affiliations":[{"raw_affiliation_string":"Old Dominion University","institution_ids":["https://openalex.org/I4210092569","https://openalex.org/I81365321"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101515728"],"corresponding_institution_ids":["https://openalex.org/I4210092569","https://openalex.org/I81365321"],"apc_list":null,"apc_paid":null,"fwci":0.1388,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57219571,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9998000264167786,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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":0.9876999855041504,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.8261365294456482},{"id":"https://openalex.org/keywords/credibility","display_name":"Credibility","score":0.8069387674331665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7513298988342285},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5377642512321472},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4883415400981903},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.47648924589157104},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4534109830856323},{"id":"https://openalex.org/keywords/behavioural-sciences","display_name":"Behavioural sciences","score":0.44313135743141174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4251954257488251},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.40217357873916626},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.23657462000846863},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.08858507871627808},{"id":"https://openalex.org/keywords/social-science","display_name":"Social science","score":0.08018684387207031}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8261365294456482},{"id":"https://openalex.org/C2780224610","wikidata":"https://www.wikidata.org/wiki/Q1530061","display_name":"Credibility","level":2,"score":0.8069387674331665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7513298988342285},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5377642512321472},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4883415400981903},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47648924589157104},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4534109830856323},{"id":"https://openalex.org/C5570062","wikidata":"https://www.wikidata.org/wiki/Q3919817","display_name":"Behavioural sciences","level":2,"score":0.44313135743141174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4251954257488251},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40217357873916626},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.23657462000846863},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.08858507871627808},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.08018684387207031},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3558100.3563855","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3558100.3563855","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3558100.3563855","source":null,"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 22nd ACM Symposium on Document Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:digitalcommons.odu.edu:computerscience_fac_pubs-1284","is_oa":true,"landing_page_url":"https://digitalcommons.odu.edu/computerscience_fac_pubs/279","pdf_url":null,"source":{"id":"https://openalex.org/S4377196314","display_name":"ODU Digital Commons (Old Dominion University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I81365321","host_organization_name":"Old Dominion University","host_organization_lineage":["https://openalex.org/I81365321"],"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":"Computer Science Faculty Publications","raw_type":"conference"}],"best_oa_location":{"id":"doi:10.1145/3558100.3563855","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3558100.3563855","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3558100.3563855","source":null,"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 22nd ACM Symposium on Document Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G8234658249","display_name":null,"funder_award_id":"W911NF-19-2-0272","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4313127206.pdf","grobid_xml":"https://content.openalex.org/works/W4313127206.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1603719052","https://openalex.org/W1907286193","https://openalex.org/W2107598941","https://openalex.org/W2250539671","https://openalex.org/W2612690371","https://openalex.org/W2755613048","https://openalex.org/W2756381707","https://openalex.org/W2883786683","https://openalex.org/W2896457183","https://openalex.org/W2915716523","https://openalex.org/W2962739339","https://openalex.org/W3011594683","https://openalex.org/W3038098779","https://openalex.org/W3046294790","https://openalex.org/W3095863931","https://openalex.org/W3102611879","https://openalex.org/W3103981637","https://openalex.org/W3155052204","https://openalex.org/W3185178825","https://openalex.org/W3194863489","https://openalex.org/W4206192903","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2388687352","https://openalex.org/W2370187191","https://openalex.org/W1990162851","https://openalex.org/W2369854048","https://openalex.org/W2374291020","https://openalex.org/W2355907197","https://openalex.org/W3171042291","https://openalex.org/W2390961115","https://openalex.org/W2388138913","https://openalex.org/W4396769302"],"abstract_inverted_index":{"Theories":[0],"and":[1,20,27,35,60,138,168],"models,":[2],"which":[3],"are":[4,170],"common":[5],"in":[6,9,51,129],"scientific":[7,52],"papers":[8],"almost":[10],"all":[11],"domains,":[12],"usually":[13],"provide":[14],"the":[15,23,33,73,140,143],"foundations":[16],"of":[17,25,37,67,75,79,109],"theoretical":[18],"analysis":[19],"experiments.":[21],"Understanding":[22],"use":[24,120],"theories":[26],"models":[28,125],"can":[29],"shed":[30],"light":[31],"on":[32,93],"credibility":[34],"reproducibility":[36],"research":[38],"works.":[39],"Compared":[40],"with":[41,146],"metadata,":[42],"such":[43],"as":[44,149,151],"title,":[45],"author,":[46],"keywords,":[47],"etc.,":[48],"theory":[49,127],"extraction":[50,128],"literature":[53],"is":[54,72,142,155],"rarely":[55],"explored,":[56],"especially":[57],"for":[58,82,126],"social":[59],"behavioral":[61],"science":[62],"(SBS)":[63],"domains.":[64],"One":[65],"challenge":[66],"applying":[68],"supervised":[69],"learning":[70,136],"methods":[71],"lack":[74],"a":[76,104,147],"large":[77],"number":[78],"labeled":[80],"samples":[81],"training.":[83],"In":[84],"this":[85,121],"paper,":[86],"we":[87],"propose":[88],"an":[89],"automated":[90],"framework":[91],"based":[92],"distant":[94],"supervision":[95],"that":[96],"leverages":[97],"entity":[98],"mentions":[99],"from":[100],"Wikipedia":[101],"to":[102,123,157,161],"build":[103],"ground":[105],"truth":[106],"corpus":[107,122],"consisting":[108],"more":[110],"than":[111,164],"4500":[112],"automatically":[113],"annotated":[114],"sentences":[115],"containing":[116],"theory/model":[117],"mentions.":[118],"We":[119,132],"train":[124],"SBS":[130],"papers.":[131],"compared":[133],"four":[134],"deep":[135],"architectures":[137],"found":[139],"RoBERTa-BiLSTM-CRF":[141],"best":[144],"one":[145],"precision":[148],"high":[150],"89.72%.":[152],"The":[153,166],"model":[154],"promising":[156],"be":[158],"conveniently":[159],"extended":[160],"domains":[162],"other":[163],"SBS.":[165],"code":[167],"data":[169],"publicly":[171],"available":[172],"at":[173],"https://github.com/lamps-lab/theory.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}