{"id":"https://openalex.org/W4390992128","doi":"https://doi.org/10.1109/bibm58861.2023.10385618","title":"Latent Topic Extraction as a Source of Labeling in Natural Language Processing","display_name":"Latent Topic Extraction as a Source of Labeling in Natural Language Processing","publication_year":2023,"publication_date":"2023-12-05","ids":{"openalex":"https://openalex.org/W4390992128","doi":"https://doi.org/10.1109/bibm58861.2023.10385618"},"language":"en","primary_location":{"id":"doi:10.1109/bibm58861.2023.10385618","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bibm58861.2023.10385618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-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/A5036325974","display_name":"Andrew Hornback","orcid":"https://orcid.org/0009-0009-5461-5848"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Hornback","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA,USA","Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010965105","display_name":"Yuanda Zhu","orcid":"https://orcid.org/0000-0001-7812-9216"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuanda Zhu","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA,USA","Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063348268","display_name":"Monica Isgut","orcid":"https://orcid.org/0000-0001-9171-8138"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Monica Isgut","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA,USA","Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034193264","display_name":"Wenqi Shi","orcid":"https://orcid.org/0000-0001-8972-7342"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenqi Shi","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA,USA","Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086621783","display_name":"Arjita Nema","orcid":null},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arjita Nema","raw_affiliation_strings":["Emory University,Atlanta,GA,USA","Emory University, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Emory University,Atlanta,GA,USA","institution_ids":["https://openalex.org/I150468666"]},{"raw_affiliation_string":"Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107722843","display_name":"Blake Anderson","orcid":"https://orcid.org/0000-0002-4956-6721"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Blake Anderson","raw_affiliation_strings":["Emory University,Atlanta,GA,USA","Emory University, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Emory University,Atlanta,GA,USA","institution_ids":["https://openalex.org/I150468666"]},{"raw_affiliation_string":"Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030096887","display_name":"May D. Wang","orcid":"https://orcid.org/0000-0003-3961-3608"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"May D. Wang","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA,USA","Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3263,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67472019,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4312","last_page":"4319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T13702","display_name":"Machine Learning in Healthcare","score":0.9958000183105469,"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":0.9952999949455261,"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/computer-science","display_name":"Computer science","score":0.813441276550293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6724823117256165},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.651003897190094},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6457464694976807},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.6177029609680176},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.4904596507549286},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.48420026898384094},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.48184049129486084},{"id":"https://openalex.org/keywords/subject-matter-expert","display_name":"Subject-matter expert","score":0.42092663049697876},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41742151975631714},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3786013424396515},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3411480784416199}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.813441276550293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6724823117256165},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.651003897190094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6457464694976807},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6177029609680176},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.4904596507549286},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.48420026898384094},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.48184049129486084},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.42092663049697876},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41742151975631714},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3786013424396515},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3411480784416199},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm58861.2023.10385618","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bibm58861.2023.10385618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W206759535","https://openalex.org/W1880262756","https://openalex.org/W1902027874","https://openalex.org/W1924770834","https://openalex.org/W2012397029","https://openalex.org/W2017365838","https://openalex.org/W2038043464","https://openalex.org/W2064675550","https://openalex.org/W2064690543","https://openalex.org/W2104210067","https://openalex.org/W2113359929","https://openalex.org/W2130339025","https://openalex.org/W2131774270","https://openalex.org/W2135384781","https://openalex.org/W2136787567","https://openalex.org/W2157331557","https://openalex.org/W2518582440","https://openalex.org/W2613831280","https://openalex.org/W2735175355","https://openalex.org/W2766140847","https://openalex.org/W2892252202","https://openalex.org/W2896457183","https://openalex.org/W2963078493","https://openalex.org/W2963716420","https://openalex.org/W2963956191","https://openalex.org/W3160137267","https://openalex.org/W4223926712","https://openalex.org/W4233135949","https://openalex.org/W4288421367","https://openalex.org/W4292779060","https://openalex.org/W4319662928","https://openalex.org/W4327946446","https://openalex.org/W4383481965","https://openalex.org/W4385245566","https://openalex.org/W6639619044","https://openalex.org/W6640212811","https://openalex.org/W6679482899","https://openalex.org/W6680930200","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W3159709618","https://openalex.org/W2611137333","https://openalex.org/W3005513013","https://openalex.org/W4389543811"],"abstract_inverted_index":{"Supervised":[0],"machine":[1,31],"learning":[2,32],"algorithms":[3,167],"depend":[4],"on":[5,45,59],"accurate":[6],"labeling":[7,140],"of":[8,35,41,48,78,116,170,175,185,197],"target":[9,23,39],"data":[10,20,43,50,89,148,213],"to":[11,52,70,87,98,168,207],"develop":[12],"models":[13,33],"that":[14,196,201],"can":[15],"derive":[16],"relationships":[17],"between":[18],"input":[19],"and":[21,92,126,153],"the":[22,37,46,49,54,72,76,84,100,114,136,139,155,165,171,176,188,198,202],"data.":[24],"One":[25],"major":[26],"hindrance":[27],"for":[28,90,134,210,216],"developing":[29,211],"supervised":[30],"capable":[34],"predicting":[36],"correct":[38],"label":[40],"unseen":[42],"rests":[44],"quality":[47],"used":[51,206,215],"train":[53,71],"models,":[55],"which":[56],"often":[57],"depends":[58],"having":[60],"a":[61,67,151,182],"subject":[62],"matter":[63],"expert":[64],"(SME)":[65],"create":[66],"labeled":[68,149,212],"dataset":[69],"model":[73],"on.":[74],"Given":[75],"scarcity":[77],"such":[79],"experts":[80],"in":[81,138,157,187],"many":[82],"fields,":[83],"time":[85],"needed":[86],"analyze":[88],"labeling,":[91],"subjective":[93],"differences":[94],"among":[95],"experts,":[96],"ways":[97],"reduce":[99],"complexity":[101],"associated":[102],"with":[103,195],"creating":[104],"meaningful":[105,218],"datasets":[106],"are":[107],"needed.":[108],"In":[109],"this":[110],"work,":[111],"we":[112,143,180],"explore":[113],"use":[115],"two":[117,166],"unsupervised":[118],"topic":[119,177],"modeling":[120,178],"algorithms,":[121,179],"Latent":[122],"Dirichlet":[123],"Allocation":[124],"(LDA)":[125],"Non-negative":[127],"Matrix":[128],"Factorization":[129],"(NMF)":[130],"as":[131,160],"potential":[132],"methods":[133],"reducing":[135],"complexities":[137],"process.":[141],"Specifically,":[142],"obtained":[144],"COVID":[145,161,189],"patient":[146,192],"message":[147,193],"by":[150,164],"SME":[152],"compared":[154],"overlap":[156,186],"topics":[158],"designated":[159],"versus":[162],"not":[163],"those":[169],"SME.":[172],"For":[173],"each":[174],"found":[181],"strong":[183],"degree":[184],"vs.":[190],"non-COVID":[191],"labels":[194],"SME,":[199],"suggesting":[200],"methodology":[203],"could":[204],"be":[205],"provide":[208],"synergies":[209],"sets":[214],"clinically":[217],"models.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}