{"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":"codex-gemma-dda1882f352a","candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006483407,0.0001920775,0.001435875,0.003893601,0.0002421331,0.00000905974,0.0003003896,0.001247438,0.00004525099],"category_scores_gemma":[0.008287677,0.0001350344,0.0002741087,0.002791459,0.0001453507,0.0005160191,0.00006740316,0.004804149,0.000002483191],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006053777,"about_ca_system_score_gemma":0.003215994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003392067,"about_ca_topic_score_gemma":0.00002248052,"domain_scores_codex":[0.9933247,0.0008117639,0.0050682,0.000115363,0.0003891852,0.0002908083],"domain_scores_gemma":[0.9900948,0.001636867,0.006887691,0.0002623963,0.001080608,0.00003759703],"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":[0.00003255674,0.00001259085,0.01239169,0.08505653,0.00003622739,0.000003275923,0.00006532302,0.00001013218,3.889588e-8,0.001281698,0.0002095443,0.9009004],"study_design_scores_gemma":[0.0007803648,0.0001827228,0.0004964792,0.3528751,0.0003258433,0.001588995,0.002610183,0.00007282374,0.000001455657,0.002851169,0.6380458,0.0001690133],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00009382205,0.9922484,0.001884297,0.001624405,0.0009545564,0.00267873,0.00001653988,0.00001581574,0.0004834582],"genre_scores_gemma":[0.0001615731,0.9964037,0.002869734,0.0001726777,0.0000777337,0.0001940958,0.0001061835,0.000006200557,0.000008109318],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9007314,"threshold_uncertainty_score":0.9974918,"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."}}