{"id":"https://openalex.org/W4287980692","doi":"https://doi.org/10.1108/el-03-2022-0071","title":"Framework for entity extraction with verification: application to inference of data set usage in research publications","display_name":"Framework for entity extraction with verification: application to inference of data set usage in research publications","publication_year":2022,"publication_date":"2022-07-26","ids":{"openalex":"https://openalex.org/W4287980692","doi":"https://doi.org/10.1108/el-03-2022-0071"},"language":"en","primary_location":{"id":"doi:10.1108/el-03-2022-0071","is_oa":false,"landing_page_url":"https://doi.org/10.1108/el-03-2022-0071","pdf_url":null,"source":{"id":"https://openalex.org/S902750600","display_name":"The Electronic Library","issn_l":"0264-0473","issn":["0264-0473","1758-616X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Electronic Library","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086089182","display_name":"Svetlozar Nestorov","orcid":null},"institutions":[{"id":"https://openalex.org/I1925986","display_name":"Loyola University Chicago","ror":"https://ror.org/04b6x2g63","country_code":"US","type":"education","lineage":["https://openalex.org/I1925986"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Svetlozar Nestorov","raw_affiliation_strings":["Department of Information Systems and Supply Chain Management, Loyola University Chicago, Chicago, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"Department of Information Systems and Supply Chain Management, Loyola University Chicago, Chicago, Illinois, USA","institution_ids":["https://openalex.org/I1925986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064731014","display_name":"Dinko Ba\u010di\u0107","orcid":"https://orcid.org/0000-0002-8819-6137"},"institutions":[{"id":"https://openalex.org/I1925986","display_name":"Loyola University Chicago","ror":"https://ror.org/04b6x2g63","country_code":"US","type":"education","lineage":["https://openalex.org/I1925986"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinko Ba\u010di\u0107","raw_affiliation_strings":["Department of Information Systems and Supply Chain Management, Loyola University Chicago, Chicago, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"Department of Information Systems and Supply Chain Management, Loyola University Chicago, Chicago, Illinois, USA","institution_ids":["https://openalex.org/I1925986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026694295","display_name":"Nenad Juki\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I1925986","display_name":"Loyola University Chicago","ror":"https://ror.org/04b6x2g63","country_code":"US","type":"education","lineage":["https://openalex.org/I1925986"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nenad Juki\u0107","raw_affiliation_strings":["Department of Information Systems and Supply Chain Management, Loyola University Chicago, Chicago, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"Department of Information Systems and Supply Chain Management, Loyola University Chicago, Chicago, Illinois, USA","institution_ids":["https://openalex.org/I1925986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028132801","display_name":"Mary Malliaris","orcid":"https://orcid.org/0000-0002-4029-4037"},"institutions":[{"id":"https://openalex.org/I1925986","display_name":"Loyola University Chicago","ror":"https://ror.org/04b6x2g63","country_code":"US","type":"education","lineage":["https://openalex.org/I1925986"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mary Malliaris","raw_affiliation_strings":["Department of Information Systems and Supply Chain Management, Loyola University Chicago, Chicago, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"Department of Information Systems and Supply Chain Management, Loyola University Chicago, Chicago, Illinois, USA","institution_ids":["https://openalex.org/I1925986"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5086089182"],"corresponding_institution_ids":["https://openalex.org/I1925986"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07350812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"4","first_page":"453","last_page":"471"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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":0.9991000294685364,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9973999857902527,"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/T11719","display_name":"Data Quality and Management","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8815256357192993},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6765305399894714},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.616962194442749},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.5960182547569275},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5544124841690063},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4833816885948181},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4492015242576599},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.440765917301178},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42381709814071655},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4178255796432495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36890560388565063}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8815256357192993},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6765305399894714},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.616962194442749},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.5960182547569275},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5544124841690063},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4833816885948181},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4492015242576599},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.440765917301178},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42381709814071655},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4178255796432495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36890560388565063},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1108/el-03-2022-0071","is_oa":false,"landing_page_url":"https://doi.org/10.1108/el-03-2022-0071","pdf_url":null,"source":{"id":"https://openalex.org/S902750600","display_name":"The Electronic Library","issn_l":"0264-0473","issn":["0264-0473","1758-616X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Electronic Library","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1503071992","https://openalex.org/W1593239840","https://openalex.org/W1908119927","https://openalex.org/W1980318031","https://openalex.org/W2004763266","https://openalex.org/W2020278455","https://openalex.org/W2039331562","https://openalex.org/W2046240631","https://openalex.org/W2072944755","https://openalex.org/W2086061894","https://openalex.org/W2092663438","https://openalex.org/W2123442489","https://openalex.org/W2131598923","https://openalex.org/W2158899491","https://openalex.org/W2169353103","https://openalex.org/W2171230211","https://openalex.org/W2315412772","https://openalex.org/W2442924240","https://openalex.org/W2492098043","https://openalex.org/W2577020101","https://openalex.org/W2603493857","https://openalex.org/W2729487522","https://openalex.org/W2785349534","https://openalex.org/W2798298921","https://openalex.org/W2870281694","https://openalex.org/W2901718007","https://openalex.org/W2945411757","https://openalex.org/W2948095805","https://openalex.org/W2962955084","https://openalex.org/W2964201789","https://openalex.org/W2972007002","https://openalex.org/W3003712253","https://openalex.org/W3011594683","https://openalex.org/W3028968453","https://openalex.org/W3047437958","https://openalex.org/W3096909640","https://openalex.org/W3098427023","https://openalex.org/W3138600255","https://openalex.org/W3187077975","https://openalex.org/W3192653863","https://openalex.org/W3203364106","https://openalex.org/W4236892377"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W2125145484","https://openalex.org/W1978971213","https://openalex.org/W1567338489","https://openalex.org/W154076710","https://openalex.org/W159132833","https://openalex.org/W38394648","https://openalex.org/W1517743118","https://openalex.org/W2398825887","https://openalex.org/W2078268723"],"abstract_inverted_index":{"Purpose":[0],"The":[1,21,142,187],"purpose":[2],"of":[3,27,198,205,225],"this":[4,100],"paper":[5,81],"is":[6,144,175],"to":[7,31],"propose":[8],"an":[9,103],"extensible":[10],"framework":[11,22,143,174,188],"for":[12,123,130,177],"extracting":[13],"data":[14,36,49,65,94],"set":[15,26,37,66,95],"usage":[16,38],"from":[17,153,169],"research":[18,156,185,207],"articles.":[19],"Design/methodology/approach":[20],"uses":[23],"a":[24,75,84,111,115,136,154,178,184,190],"training":[25],"manually":[28],"labeled":[29],"examples":[30],"identify":[32],"word":[33,42,124],"features":[34,43],"surrounding":[35],"references.":[39],"Using":[40],"the":[41,57,63,72,98,120,172,195,199,203,206,219,223],"and":[44,53,59,132,134],"general":[45,215],"entity":[46,88,167],"identifiers,":[47],"candidate":[48],"sets":[50],"are":[51],"extracted":[52,64],"scored":[54],"separately":[55],"at":[56],"sentence":[58],"document":[60],"levels.":[61],"Finally,":[62],"references":[67],"can":[68],"be":[69],"verified":[70],"by":[71,91,151,202],"authors":[73,204],"using":[74],"web-based":[76,138],"verification":[77,140,191],"module.":[78],"Findings":[79],"This":[80,209],"successfully":[82,145],"addresses":[83],"significant":[85],"gap":[86],"in":[87],"extraction":[89],"literature":[90],"focusing":[92],"on":[93,147,163],"extraction.":[96],"In":[97],"process,":[99],"paper:":[101],"identified":[102],"entity-extraction":[104],"scenario":[105,221],"with":[106,214],"specific":[107],"characteristics":[108],"that":[109,193],"enable":[110],"multiphase":[112],"approach,":[113],"including":[114],"feasible":[116],"author-verification":[117],"step;":[118],"defined":[119,127],"search":[121],"space":[122],"feature":[125],"identification;":[126],"scoring":[128],"functions":[129],"sentences":[131],"documents;":[133],"designed":[135,176],"simple":[137],"author":[139,227],"step.":[141],"tested":[146],"178":[148],"articles":[149],"authored":[150],"researchers":[152],"large":[155],"organization.":[157],"Originality/value":[158],"Whereas":[159],"previous":[160],"approaches":[161],"focused":[162],"completely":[164],"automated":[165],"large-scale":[166],"recognition":[168],"text":[170],"snippets,":[171],"proposed":[173],"longer,":[179],"high-quality":[180],"text,":[181],"such":[182],"as":[183],"publication.":[186],"includes":[189],"module":[192,210],"enables":[194],"request":[196],"validation":[197],"discovered":[200],"entities":[201],"publications.":[208],"shares":[211],"some":[212],"similarities":[213],"crowdsourcing":[216],"approaches,":[217],"but":[218],"target":[220],"increases":[222],"likelihood":[224],"meaningful":[226],"participation.":[228]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}