{"id":"W4409046432","doi":"10.36680/j.itcon.2025.019","title":"A review of machine learning for analysing accident reports in the construction industry","year":2025,"lang":"en","type":"review","venue":"Journal of Information Technology in Construction","topic":"Occupational Health and Safety Research","field":"Health Professions","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Innovation Cluster (Canada)","funders":"","keywords":"Context (archaeology); Computer science; CLARITY; Artificial intelligence; Machine learning; Structuring; Unstructured data; Unsupervised learning; Data science; Accident (philosophy); Natural language processing; Data mining; Big data","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003954352,0.001075688,0.00150342,0.01060909,0.0004172119,0.00172919,0.001556503,0.001511923,0.00286654],"category_scores_gemma":[0.01359908,0.0006463114,0.001962563,0.009296586,0.0007263141,0.002856942,0.0007580857,0.001248134,0.001107995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001583665,"about_ca_system_score_gemma":0.004079558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004345141,"about_ca_topic_score_gemma":0.005656166,"domain_scores_codex":[0.9971086,0.00086829,0.000778864,0.0003610089,0.0008056243,0.00007746619],"domain_scores_gemma":[0.9820735,0.01398057,0.001223047,0.0002498795,0.002331068,0.0001419612],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006240809,0.00005944491,0.001025917,0.125567,0.000376641,0.0002335353,0.0003672539,0.0009327454,0.0007282884,0.003469472,0.01851203,0.8486652],"study_design_scores_gemma":[0.00002013358,0.0002541796,0.00845177,0.1284012,0.001329495,0.00142783,0.0005292067,0.001071801,0.00148721,0.004397193,0.8525133,0.0001167842],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0002831084,0.9966307,0.001285145,0.0005328091,0.0002367601,0.00002746875,0.0000936095,0.00001769364,0.0008926704],"genre_scores_gemma":[0.001980029,0.9949266,0.002136927,0.0003215247,0.0002349352,0.00003733985,0.0001291639,0.000006755879,0.0002267058],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.01060909,"threshold_uncertainty_score":0.02091289,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06125469995933066,"score_gpt":0.4964780754303192,"score_spread":0.4352233754709886,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}