{"id":"W4388773811","doi":"10.1016/j.eswa.2023.122582","title":"A machine learning tool for collecting and analyzing subjective road safety data from Twitter","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Support vector machine; Naive Bayes classifier; Random forest; Artificial intelligence; Machine learning; Crowdsourcing; Classifier (UML); Social media; World Wide Web","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0004610879,0.0001284396,0.0002222034,0.0001539375,0.000646107,0.000312812,0.000519864,0.00003637861,0.000004859025],"category_scores_gemma":[0.00003656761,0.0001063274,0.00003132911,0.0009661286,0.00001985653,0.0003003547,0.0002828927,0.0000840979,0.00002466558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003403365,"about_ca_system_score_gemma":0.00003619689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005490248,"about_ca_topic_score_gemma":0.00003386026,"domain_scores_codex":[0.9986441,0.00005910454,0.0002764026,0.0006374962,0.0001725691,0.000210377],"domain_scores_gemma":[0.9986547,0.0003358001,0.0001641018,0.0007104519,0.00007823917,0.00005669932],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004500803,0.0006333346,0.4951946,0.0004286725,0.00616693,0.00003466709,0.09065058,0.02897009,0.03231378,0.04547076,0.06488445,0.234802],"study_design_scores_gemma":[0.0004142957,0.00002404399,0.002330878,0.00004742365,0.00001974755,0.000003625858,0.00103284,0.9389643,0.00006241265,0.00004177593,0.05686944,0.0001891938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006287328,0.001081369,0.9909116,0.0004139738,0.00007549875,0.00072609,0.0000346435,0.0002419754,0.000227512],"genre_scores_gemma":[0.9410623,0.0001781249,0.05303261,0.0001293869,0.0006147279,0.001794402,0.001054008,0.00004298616,0.00209142],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.937879,"threshold_uncertainty_score":0.4969398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05363648456002865,"score_gpt":0.3167575060949625,"score_spread":0.2631210215349339,"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."}}