{"id":"W7117479044","doi":"10.1080/17538947.2025.2604977","title":"A systematic review and comparative analysis of deep learning models for Twitter/X-based traffic event detection","year":2025,"lang":"en","type":"article","venue":"International Journal of Digital Earth","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Deep learning; Big data; Event (particle physics); Pipeline (software); Traffic flow (computer networking); Intelligent transportation system","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":[0.0001421019,0.00006551125,0.0003205439,0.0004552661,0.00001106997,0.00004461144,0.00009510793,0.00001743384,0.000001672045],"category_scores_gemma":[0.00004202444,0.00005730802,0.0001668751,0.0001813428,0.0000127789,0.0002165355,0.000008735179,0.00006429813,1.790705e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002869315,"about_ca_system_score_gemma":0.000006949212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":2.554901e-7,"about_ca_topic_score_gemma":0.000004193996,"domain_scores_codex":[0.99931,0.00001421895,0.0004296425,0.00004978909,0.0001505643,0.00004584856],"domain_scores_gemma":[0.9994925,0.00007376476,0.0001667048,0.00003920427,0.0002072398,0.00002063005],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003080943,0.00005108502,0.00002998338,0.009177636,0.004178105,0.000001646888,0.0001222851,0.9783329,0.00007066451,0.0005023528,0.0001066238,0.007395887],"study_design_scores_gemma":[0.0002759254,0.00007007534,0.0001485572,0.004179342,0.001325505,0.000003434367,0.00007842948,0.9934402,0.0002768398,0.00005427094,0.00009613335,0.00005129786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01792441,0.002784365,0.9781074,0.00006217818,0.0001047883,0.0002441055,0.00001014908,0.000100241,0.0006623468],"genre_scores_gemma":[0.9993089,0.0003073004,0.0002795909,0.00004565606,0.000007373219,0.00001203064,0.000006562755,0.000002783299,0.00002976084],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9813845,"threshold_uncertainty_score":0.2336953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01806764615980464,"score_gpt":0.2700242492244732,"score_spread":0.2519566030646685,"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."}}