{"id":"https://openalex.org/W4406458722","doi":"https://doi.org/10.1109/bigdata62323.2024.10825997","title":"Empirical Evaluation of Embedding Models in the Context of Text Classification in Document Review in Construction Delay Disputes","display_name":"Empirical Evaluation of Embedding Models in the Context of Text Classification in Document Review in Construction Delay Disputes","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406458722","doi":"https://doi.org/10.1109/bigdata62323.2024.10825997"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5052463733","display_name":"Fusheng Wei","orcid":"https://orcid.org/0009-0000-5881-5307"},"institutions":[{"id":"https://openalex.org/I68939703","display_name":"Fujikura (United States)","ror":"https://ror.org/00qpbjw91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210098230","https://openalex.org/I68939703"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fusheng Wei","raw_affiliation_strings":["Ankura Consulting Group, LLC,Data & Technology,Washington, D.C.,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ankura Consulting Group, LLC,Data & Technology,Washington, D.C.,USA","institution_ids":["https://openalex.org/I68939703"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042371258","display_name":"Robert Neary","orcid":null},"institutions":[{"id":"https://openalex.org/I68939703","display_name":"Fujikura (United States)","ror":"https://ror.org/00qpbjw91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210098230","https://openalex.org/I68939703"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Neary","raw_affiliation_strings":["Ankura Consulting Group, LLC,Data & Technology,Washington, D.C.,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ankura Consulting Group, LLC,Data & Technology,Washington, D.C.,USA","institution_ids":["https://openalex.org/I68939703"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101414674","display_name":"Han Qin","orcid":"https://orcid.org/0000-0003-3786-3910"},"institutions":[{"id":"https://openalex.org/I68939703","display_name":"Fujikura (United States)","ror":"https://ror.org/00qpbjw91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210098230","https://openalex.org/I68939703"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Qin","raw_affiliation_strings":["Ankura Consulting Group, LLC,Data & Technology,Washington, D.C.,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ankura Consulting Group, LLC,Data & Technology,Washington, D.C.,USA","institution_ids":["https://openalex.org/I68939703"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101453263","display_name":"Qiang Mao","orcid":"https://orcid.org/0000-0002-9382-6527"},"institutions":[{"id":"https://openalex.org/I68939703","display_name":"Fujikura (United States)","ror":"https://ror.org/00qpbjw91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210098230","https://openalex.org/I68939703"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiang Mao","raw_affiliation_strings":["Ankura Consulting Group, LLC,Data & Technology,Washington, D.C.,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ankura Consulting Group, LLC,Data & Technology,Washington, D.C.,USA","institution_ids":["https://openalex.org/I68939703"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100390066","display_name":"Jianping Zhang","orcid":"https://orcid.org/0000-0001-7141-9464"},"institutions":[{"id":"https://openalex.org/I68939703","display_name":"Fujikura (United States)","ror":"https://ror.org/00qpbjw91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210098230","https://openalex.org/I68939703"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianping Zhang","raw_affiliation_strings":["Ankura Consulting Group, LLC,Data & Technology,Washington, D.C.,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ankura Consulting Group, LLC,Data & Technology,Washington, D.C.,USA","institution_ids":["https://openalex.org/I68939703"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I68939703"],"apc_list":null,"apc_paid":null,"fwci":4.8964,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95980726,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4763","last_page":"4767"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.9337000250816345,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"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/T13643","display_name":"Artificial Intelligence in Law","score":0.9337000250816345,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"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":0.713701605796814},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6994940042495728},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6326767206192017},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5616954565048218},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.5052903294563293},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42055752873420715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37045958638191223},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3237376809120178},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3223307728767395},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12125495076179504},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10084125399589539},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08201843500137329}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.713701605796814},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6994940042495728},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6326767206192017},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5616954565048218},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.5052903294563293},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42055752873420715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37045958638191223},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3237376809120178},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3223307728767395},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12125495076179504},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10084125399589539},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08201843500137329},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2970641574","https://openalex.org/W4205807230","https://openalex.org/W6767552790","https://openalex.org/W6769627184"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2037549926","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W2419146053","https://openalex.org/W4388890789","https://openalex.org/W2088247287","https://openalex.org/W2963903416"],"abstract_inverted_index":{"Text":[0],"embeddings":[1,22,41,75,131],"are":[2,14],"numerical":[3,56],"representations":[4],"of":[5,18,39,47,81,128,147,153,159,168],"text":[6,29,40,48,88,110,129,135],"data,":[7],"where":[8],"words,":[9],"phrases,":[10],"or":[11,116],"entire":[12],"documents":[13],"converted":[15],"into":[16],"vectors":[17],"real":[19],"numbers.":[20],"These":[21],"capture":[23],"semantic":[24],"meanings":[25],"and":[26,97,166],"relationships":[27],"between":[28],"elements":[30],"in":[31,72,171,181],"a":[32,77,109,120],"continuous":[33],"vector":[34],"space.":[35],"The":[36,151],"primary":[37],"goal":[38],"is":[42,112],"to":[43,101,138,162],"enable":[44],"the":[45,126,143,157,164,175],"processing":[46],"data":[49],"by":[50],"machine":[51],"learning":[52],"models,":[53,84],"which":[54],"require":[55],"input.":[57],"Numerous":[58],"embedding":[59,160],"models":[60,137,161],"have":[61],"been":[62],"developed":[63],"for":[64,132,177],"various":[65],"applications.":[66],"This":[67],"paper":[68],"presents":[69],"our":[70],"work":[71],"evaluating":[73],"different":[74],"through":[76],"comprehensive":[78],"comparative":[79],"analysis":[80,170],"four":[82],"distinct":[83],"focusing":[85],"on":[86],"their":[87],"classification":[89,104,136],"efficacy.":[90],"We":[91],"employ":[92],"both":[93],"K-Nearest":[94],"Neighbors":[95],"(KNN)":[96],"Logistic":[98],"Regression":[99],"(LR)":[100],"perform":[102],"binary":[103],"tasks,":[105],"specifically":[106],"determining":[107],"whether":[108],"snippet":[111,130],"associated":[113],"with":[114],"'delay'":[115],"'not":[117],"delay'":[118],"within":[119],"labeled":[121],"dataset.":[122],"Our":[123],"research":[124],"explores":[125],"use":[127],"training":[133],"supervised":[134],"identify":[139],"delay-related":[140],"statements":[141],"during":[142],"document":[144,169],"review":[145],"process":[146],"construction":[148],"delay":[149],"disputes.":[150],"results":[152],"this":[154],"study":[155],"highlight":[156],"potential":[158],"enhance":[163],"efficiency":[165],"accuracy":[167],"legal":[172],"contexts,":[173],"paving":[174],"way":[176],"more":[178],"informed":[179],"decision-making":[180],"complex":[182],"investigative":[183],"scenarios.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}