{"id":"https://openalex.org/W7216339504","doi":"https://doi.org/10.1038/s41598-026-73518-3","title":"A hybrid machine learning framework integrating persian NLP for occupational risk classification in steel manufacturing","display_name":"A hybrid machine learning framework integrating persian NLP for occupational risk classification in steel manufacturing","publication_year":2026,"publication_date":"2026-10-02","ids":{"openalex":"https://openalex.org/W7216339504","doi":"https://doi.org/10.1038/s41598-026-73518-3"},"language":"en","primary_location":{"id":"doi:10.1038/s41598-026-73518-3","doi":"https://doi.org/10.1038/s41598-026-73518-3","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-73518-3","pdf_url":"https://www.nature.com/articles/s41598-026-73518-3_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.nature.com/articles/s41598-026-73518-3_reference.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139070674","display_name":"Ensieh Sadat Alamshah","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161106909","display_name":"Iran University of Medical Sciences","ror":"https://ror.org/03w04rv71","country_code":"IR","type":"education","lineage":["https://openalex.org/I161106909"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Ensieh Sadat Alamshah","raw_affiliation_strings":["Student Research Committee, School of Public Health,  Iran University of Medical Sciences, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Student Research Committee, School of Public Health,  Iran University of Medical Sciences, Tehran, Iran","institution_ids":["https://openalex.org/I161106909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115610588","display_name":"Maryam Soleimani-Alyar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161106909","display_name":"Iran University of Medical Sciences","ror":"https://ror.org/03w04rv71","country_code":"IR","type":"education","lineage":["https://openalex.org/I161106909"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Maryam Soleimani-Alyar","raw_affiliation_strings":["Air Pollution Research Center, Preventive Medicine and Public Health Research Center, Psychosocial Health Research Institute, Iran University of Medical Sciences, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Air Pollution Research Center, Preventive Medicine and Public Health Research Center, Psychosocial Health Research Institute, Iran University of Medical Sciences, Tehran, Iran","institution_ids":["https://openalex.org/I161106909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008749207","display_name":"Saber Moradi Hanifi","orcid":"https://orcid.org/0000-0002-5692-2587","observed_orcids":["https://orcid.org/0000-0002-5692-2587"]},"institutions":[{"id":"https://openalex.org/I161106909","display_name":"Iran University of Medical Sciences","ror":"https://ror.org/03w04rv71","country_code":"IR","type":"education","lineage":["https://openalex.org/I161106909"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Saber Moradi Hanifi","raw_affiliation_strings":["Occupational Health Research Center, Department of Occupational Health Engineering, School of Public Health, Iran University of Medical Sciences, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Occupational Health Research Center, Department of Occupational Health Engineering, School of Public Health, Iran University of Medical Sciences, Tehran, Iran","institution_ids":["https://openalex.org/I161106909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077143894","display_name":"Behnoush Jafari","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I119939603","display_name":"Ahvaz Jundishapur University of Medical Sciences","ror":"https://ror.org/01rws6r75","country_code":"IR","type":"education","lineage":["https://openalex.org/I119939603"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Behnoush Jafari","raw_affiliation_strings":["Department of Occupational Health, School of Health, Jundishapur University of Medical Sciences, Ahvaz, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Occupational Health, School of Health, Jundishapur University of Medical Sciences, Ahvaz, Iran","institution_ids":["https://openalex.org/I119939603"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124879608","display_name":"Mahsa Behravesh","orcid":"https://orcid.org/0000-0001-6561-938X","observed_orcids":["https://orcid.org/0000-0001-6561-938X"]},"institutions":[{"id":"https://openalex.org/I161106909","display_name":"Iran University of Medical Sciences","ror":"https://ror.org/03w04rv71","country_code":"IR","type":"education","lineage":["https://openalex.org/I161106909"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Mahsa Behravesh","raw_affiliation_strings":["Student Research Committee, School of Public Health,  Iran University of Medical Sciences, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Student Research Committee, School of Public Health,  Iran University of Medical Sciences, Tehran, Iran","institution_ids":["https://openalex.org/I161106909"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5115610588"],"corresponding_institution_ids":["https://openalex.org/I161106909"],"apc_list":{"value":2690,"currency":"USD","value_usd":2690},"apc_paid":{"value":2690,"currency":"USD","value_usd":2690},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66778023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.358599990606308,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.358599990606308,"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":0.1979999989271164,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13233","display_name":"Occupational Health and Safety Management","score":0.11990000307559967,"subfield":{"id":"https://openalex.org/subfields/3609","display_name":"Occupational Therapy"},"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/occupational-risk-classification","display_name":"occupational risk classification","score":0.968999981880188},{"id":"https://openalex.org/keywords/steelmaking","display_name":"steel industry","score":0.9210000038146973},{"id":"https://openalex.org/keywords/hazard-identification","display_name":"hazard identification","score":0.7860000133514404},{"id":"https://openalex.org/keywords/job-safety-analysis","display_name":"job safety analysis","score":0.7419999837875366},{"id":"https://openalex.org/keywords/william-fine-method","display_name":"William Fine method","score":0.9350000023841858},{"id":"https://openalex.org/keywords/quantitative-risk-assessment","display_name":"quantitative risk assessment","score":0.6269999742507935},{"id":"https://openalex.org/keywords/human-error","display_name":"human error","score":0.6660000085830688},{"id":"https://openalex.org/keywords/occupational-accidents","display_name":"occupational accidents","score":0.8379999995231628},{"id":"https://openalex.org/keywords/unstructured-text","display_name":"unstructured text","score":0.6610000133514404},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.7279999852180481},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"support vector machine","score":0.8259999752044678},{"id":"https://openalex.org/keywords/industrial-safety-monitoring","display_name":"industrial safety monitoring","score":0.47699999809265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7451000213623047},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7366999983787537},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7098000049591064},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.7081999778747559},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6990000009536743},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5837000012397766},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.44850000739097595},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.42309999465942383},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3919000029563904},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C49261128","wikidata":"https://www.wikidata.org/wiki/Q1132455","display_name":"Hazard","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31349998712539673},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.31130000948905945},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1038/s41598-026-73518-3","doi":"https://doi.org/10.1038/s41598-026-73518-3","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-73518-3","pdf_url":"https://www.nature.com/articles/s41598-026-73518-3_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1038/s41598-026-73518-3","doi":"https://doi.org/10.1038/s41598-026-73518-3","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-73518-3","pdf_url":"https://www.nature.com/articles/s41598-026-73518-3_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7257999777793884,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"},{"score":0.428600013256073,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313199","display_name":"Iran University of Medical Sciences","ror":"https://ror.org/03w04rv71"},{"id":"https://openalex.org/F4320337173","display_name":"Student Research Committee, Tabriz University of Medical Sciences","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7216339504.pdf","grobid_xml":"https://content.openalex.org/works/W7216339504.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1521145432","https://openalex.org/W1994277136","https://openalex.org/W2084305090","https://openalex.org/W2207774637","https://openalex.org/W2259351402","https://openalex.org/W2460755166","https://openalex.org/W2748917130","https://openalex.org/W2771786928","https://openalex.org/W2919115771","https://openalex.org/W2952557996","https://openalex.org/W2981915020","https://openalex.org/W2998425304","https://openalex.org/W3008502799","https://openalex.org/W3209155894","https://openalex.org/W4307592886","https://openalex.org/W4385340665","https://openalex.org/W4395063705","https://openalex.org/W4404838552"],"related_works":["https://openalex.org/W7151063236","https://openalex.org/W7219092455","https://openalex.org/W4409709573","https://openalex.org/W7166662050","https://openalex.org/W7155617131","https://openalex.org/W4392357545","https://openalex.org/W2936959840","https://openalex.org/W7211945009","https://openalex.org/W7160901246","https://openalex.org/W7131812885"],"abstract_inverted_index":{"Human":[0],"error":[1],"remains":[2],"a":[3,31,65,268],"leading":[4],"cause":[5],"of":[6,165,245,257],"occupational":[7],"accidents":[8],"in":[9,22,50,64,276],"high-risk":[10,174,260,277],"industries,":[11],"yet":[12],"traditional":[13,134,230],"risk":[14,38,75,86,190,231],"assessment":[15,232],"methods":[16,233],"often":[17],"overlook":[18],"valuable":[19],"information":[20],"embedded":[21],"unstructured":[23,102,240],"textual":[24,241],"data.":[25],"This":[26,265],"study":[27],"develops":[28],"and":[29,101,116,149,168,173,239,259],"validates":[30],"hybrid":[32,226],"machine":[33,135],"learning":[34,136],"framework":[35,227],"combining":[36],"structured":[37,96,237],"data":[39,238],"with":[40,163],"Natural":[41],"Language":[42],"Processing":[43],"(NLP)":[44],"to":[45,206],"improve":[46],"hazard":[47],"classification":[48,256],"accuracy":[49,161],"industrial":[51,278],"settings.":[52],"Data":[53],"were":[54,119,138],"collected":[55],"from":[56],"258":[57],"work":[58],"activities":[59],"across":[60,184],"16":[61],"operational":[62],"units":[63],"steel":[66],"manufacturing":[67],"facility":[68],"over":[69],"five":[70],"months,":[71],"yielding":[72],"3,110":[73],"validated":[74],"scenarios.":[76],"Hazard":[77],"identification":[78],"employed":[79],"Job":[80],"Safety":[81],"Analysis":[82],"(JSA),":[83],"while":[84,254],"quantitative":[85],"evaluation":[87],"used":[88],"the":[89,159,193,207,222],"William":[90],"Fine":[91],"method.":[92],"The":[93,225,243],"dataset":[94],"comprised":[95],"variables":[97],"(severity,":[98],"exposure,":[99],"probability)":[100],"Persian-language":[103],"text":[104],"(hazard":[105],"descriptions,":[106],"locations,":[107],"activities).":[108],"Text":[109],"preprocessing":[110],"included":[111],"tokenization,":[112],"stopword":[113],"removal,":[114],"stemming,":[115],"lemmatization.":[117],"Features":[118],"extracted":[120],"using":[121],"TF-IDF":[122],"vectorization":[123],"for":[124,170,188,270],"all":[125],"models.":[126],"Random":[127,143],"Over-Sampling":[128],"(ROS)":[129],"addressed":[130],"class":[131],"imbalance.":[132],"Four":[133],"algorithms":[137],"evaluated:":[139],"Logistic":[140],"Regression":[141],"(LR),":[142],"Forest":[144],"(RF),":[145],"K-Nearest":[146],"Neighbors":[147],"(KNN),":[148],"Support":[150],"Vector":[151],"Machine":[152],"(SVM).":[153],"On":[154],"unbalanced":[155],"data,":[156],"SVM":[157,215],"achieved":[158],"highest":[160],"(93%),":[162],"F1-scores":[164],"0.96,":[166],"0.83,":[167],"0.92":[169],"low,":[171],"medium,":[172],"categories,":[175],"respectively.":[176],"After":[177],"ROS":[178],"balancing,":[179],"performance":[180],"showed":[181],"practical":[182],"improvements":[183],"most":[185],"models,":[186],"particularly":[187],"minority":[189],"classes;":[191],"however,":[192],"difference":[194],"did":[195],"not":[196],"reach":[197],"conventional":[198],"statistical":[199],"significance":[200],"(p":[201],"=":[202,212],"0.189),":[203],"likely":[204],"due":[205],"small":[208],"comparison":[209],"sample":[210],"(n":[211],"3":[213],"models).":[214],"reached":[216],"near-perfect":[217],"classification,":[218],"whereas":[219],"KNN":[220],"remained":[221],"weakest":[223],"performer.":[224],"significantly":[228],"outperforms":[229],"by":[234],"leveraging":[235],"both":[236],"information.":[242],"prevalence":[244],"low-risk":[246],"scenarios":[247],"(66.1%)":[248],"suggests":[249],"effective":[250],"existing":[251],"safety":[252,273],"controls,":[253],"improved":[255],"medium":[258],"cases":[261],"enables":[262],"targeted":[263],"interventions.":[264],"approach":[266],"provides":[267],"foundation":[269],"real-time":[271],"AI-driven":[272],"monitoring":[274],"systems":[275],"sectors.":[279]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-03T00:00:00"}