{"id":"https://openalex.org/W4410783850","doi":"https://doi.org/10.3390/a18060317","title":"AI for Data Quality Auditing: Detecting Mislabeled Work Zone Crashes Using Large Language Models","display_name":"AI for Data Quality Auditing: Detecting Mislabeled Work Zone Crashes Using Large Language Models","publication_year":2025,"publication_date":"2025-05-27","ids":{"openalex":"https://openalex.org/W4410783850","doi":"https://doi.org/10.3390/a18060317"},"language":"en","primary_location":{"id":"doi:10.3390/a18060317","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a18060317","pdf_url":"https://www.mdpi.com/1999-4893/18/6/317/pdf?version=1748335943","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/18/6/317/pdf?version=1748335943","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099111595","display_name":"Shadi Jaradat","orcid":"https://orcid.org/0000-0001-6322-2792"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shadi Jaradat","raw_affiliation_strings":["Australian International Institute of Higher Education, Brisbane 4000, Australia","Centre of Data Science, Queensland University of Technology, Brisbane 4000, Australia","Cogninet Australia, Sydney 2010, Australia"],"affiliations":[{"raw_affiliation_string":"Australian International Institute of Higher Education, Brisbane 4000, Australia","institution_ids":[]},{"raw_affiliation_string":"Centre of Data Science, Queensland University of Technology, Brisbane 4000, Australia","institution_ids":["https://openalex.org/I160993911"]},{"raw_affiliation_string":"Cogninet Australia, Sydney 2010, Australia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085400166","display_name":"Nirmal Acharya","orcid":"https://orcid.org/0000-0002-2132-5184"},"institutions":[{"id":"https://openalex.org/I74899385","display_name":"Central Queensland University","ror":"https://ror.org/023q4bk22","country_code":"AU","type":"education","lineage":["https://openalex.org/I74899385"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Nirmal Acharya","raw_affiliation_strings":["Australian International Institute of Higher Education, Brisbane 4000, Australia","Cogninet Australia, Sydney 2010, Australia","School of Business and Law, Central Queensland University, Brisbane 4000, Australia"],"affiliations":[{"raw_affiliation_string":"Australian International Institute of Higher Education, Brisbane 4000, Australia","institution_ids":[]},{"raw_affiliation_string":"Cogninet Australia, Sydney 2010, Australia","institution_ids":[]},{"raw_affiliation_string":"School of Business and Law, Central Queensland University, Brisbane 4000, Australia","institution_ids":["https://openalex.org/I74899385"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115028212","display_name":"Smitha Shivshankar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Smitha Shivshankar","raw_affiliation_strings":["Australian International Institute of Higher Education, Brisbane 4000, Australia"],"affiliations":[{"raw_affiliation_string":"Australian International Institute of Higher Education, Brisbane 4000, Australia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110937486","display_name":"Taqwa I. Alhadidi","orcid":null},"institutions":[{"id":"https://openalex.org/I104941359","display_name":"Al-Ahliyya Amman University","ror":"https://ror.org/00xddhq60","country_code":"JO","type":"education","lineage":["https://openalex.org/I104941359"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Taqwa I. Alhadidi","raw_affiliation_strings":["Faculty of Engineering, Hourani Center for Applied Scientific Research, Al-Ahliyya Amman University, Amman 19111, Jordan"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Hourani Center for Applied Scientific Research, Al-Ahliyya Amman University, Amman 19111, Jordan","institution_ids":["https://openalex.org/I104941359"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048069896","display_name":"Mohammed Elhenawy","orcid":null},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Mohammad Elhenawy","raw_affiliation_strings":["Centre of Data Science, Queensland University of Technology, Brisbane 4000, Australia"],"affiliations":[{"raw_affiliation_string":"Centre of Data Science, Queensland University of Technology, Brisbane 4000, Australia","institution_ids":["https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5048069896"],"corresponding_institution_ids":["https://openalex.org/I160993911"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":16.8533,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.99057082,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"18","issue":"6","first_page":"317","last_page":"317"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9914000034332275,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9914000034332275,"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"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.970300018787384,"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/T10809","display_name":"Occupational Health and Safety Research","score":0.9660999774932861,"subfield":{"id":"https://openalex.org/subfields/3614","display_name":"Radiological and Ultrasound Technology"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6516649127006531},{"id":"https://openalex.org/keywords/audit","display_name":"Audit","score":0.6360750198364258},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5984150767326355},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.5969793200492859},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.47992759943008423},{"id":"https://openalex.org/keywords/work-zone","display_name":"Work zone","score":0.4699670970439911},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4089174270629883},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34763896465301514},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3366104066371918},{"id":"https://openalex.org/keywords/accounting","display_name":"Accounting","score":0.13317370414733887},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10153651237487793},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.10065034031867981},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.07139468193054199}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6516649127006531},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.6360750198364258},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5984150767326355},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.5969793200492859},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.47992759943008423},{"id":"https://openalex.org/C2993327422","wikidata":"https://www.wikidata.org/wiki/Q4181026","display_name":"Work zone","level":3,"score":0.4699670970439911},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4089174270629883},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34763896465301514},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3366104066371918},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.13317370414733887},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10153651237487793},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.10065034031867981},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.07139468193054199},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/a18060317","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a18060317","pdf_url":"https://www.mdpi.com/1999-4893/18/6/317/pdf?version=1748335943","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7f78e32327a74419931d2e689bd17c83","is_oa":true,"landing_page_url":"https://doaj.org/article/7f78e32327a74419931d2e689bd17c83","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms, Vol 18, Iss 6, p 317 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/a18060317","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a18060317","pdf_url":"https://www.mdpi.com/1999-4893/18/6/317/pdf?version=1748335943","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410783850.pdf","grobid_xml":"https://content.openalex.org/works/W4410783850.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W27713786","https://openalex.org/W645118296","https://openalex.org/W1966716734","https://openalex.org/W1976526581","https://openalex.org/W2025276353","https://openalex.org/W2037579231","https://openalex.org/W2042103789","https://openalex.org/W2065633479","https://openalex.org/W2122696206","https://openalex.org/W2137429175","https://openalex.org/W2790115965","https://openalex.org/W2922778942","https://openalex.org/W3011691914","https://openalex.org/W3171501718","https://openalex.org/W4213323449","https://openalex.org/W4232166535","https://openalex.org/W4300846453","https://openalex.org/W4303614602","https://openalex.org/W4310179088","https://openalex.org/W4379469180","https://openalex.org/W4386448215","https://openalex.org/W4387422660","https://openalex.org/W4387932094","https://openalex.org/W4388655144","https://openalex.org/W4388723259","https://openalex.org/W4391559941","https://openalex.org/W4392455866","https://openalex.org/W4396709640","https://openalex.org/W4396792104","https://openalex.org/W4399729554","https://openalex.org/W4400520863","https://openalex.org/W4403094538","https://openalex.org/W4404613218","https://openalex.org/W4406863879","https://openalex.org/W4407985696","https://openalex.org/W4408127912","https://openalex.org/W4408252407","https://openalex.org/W4409332187","https://openalex.org/W6659965354","https://openalex.org/W6855717657","https://openalex.org/W6865192527"],"related_works":["https://openalex.org/W349583328","https://openalex.org/W27713786","https://openalex.org/W2331857724","https://openalex.org/W3153829552","https://openalex.org/W605689207","https://openalex.org/W2347963019","https://openalex.org/W2111864431","https://openalex.org/W317577733","https://openalex.org/W3193346540","https://openalex.org/W2404937507"],"abstract_inverted_index":{"Ensuring":[0],"high":[1],"data":[2,25,174,179],"quality":[3,180],"in":[4,126],"traffic":[5,155],"crash":[6,24,48,68,166],"datasets":[7],"is":[8,160],"critical":[9],"for":[10,22,109,146,178],"effective":[11],"safety":[12,156],"analysis":[13],"and":[14,50,75,106,149,172],"policymaking.":[15],"This":[16,130],"study":[17],"presents":[18],"an":[19,127],"AI-assisted":[20],"framework":[21,159],"auditing":[23,139],"integrity":[26],"by":[27],"detecting":[28],"potentially":[29],"mislabeled":[30],"records":[31,86],"related":[32],"to":[33,57,66,70,94,163],"construction":[34],"zone":[35,60],"(czone)":[36],"involvement.":[37,61],"A":[38],"GPT-3.5":[39],"model":[40,63,100],"was":[41,64],"fine-tuned":[42],"using":[43],"a":[44,137],"fusion":[45],"of":[46,142,153],"structured":[47,171],"attributes":[49,167],"unstructured":[51,173],"narrative":[52],"text":[53],"(i.e.,":[54],"multimodal":[55],"input)":[56],"predict":[58],"work":[59],"The":[62,99,158],"applied":[65],"6400":[67],"reports":[69],"flag":[71],"discrepancies":[72],"between":[73],"predicted":[74],"recorded":[76],"labels.":[77],"Among":[78],"80":[79],"flagged":[80],"mismatches,":[81],"expert":[82,147],"review":[83,148],"confirmed":[84],"four":[85],"as":[87,136],"genuine":[88],"misclassifications,":[89],"demonstrating":[90],"the":[91,110,144,151],"framework\u2019s":[92],"capacity":[93],"surface":[95],"high-confidence":[96],"labeling":[97],"errors.":[98],"achieved":[101],"strong":[102],"overall":[103],"accuracy":[104],"(98.75%)":[105],"precision":[107],"(86.67%)":[108],"minority":[111],"class,":[112],"but":[113],"showed":[114],"low":[115],"recall":[116],"(14.29%),":[117],"reflecting":[118],"its":[119,134],"conservative":[120],"design":[121],"that":[122],"minimizes":[123],"false":[124],"positives":[125],"imbalanced":[128],"dataset.":[129],"precision-focused":[131],"approach":[132],"supports":[133],"use":[135],"semi-automated":[138],"tool,":[140],"capable":[141],"narrowing":[143],"scope":[145],"improving":[150],"reliability":[152],"large-scale":[154],"datasets.":[157],"also":[161],"adaptable":[162],"other":[164],"misclassified":[165],"or":[168],"domains":[169],"where":[170],"can":[175],"be":[176],"fused":[177],"assurance.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":8}],"updated_date":"2026-03-30T08:08:38.191290","created_date":"2025-10-10T00:00:00"}