{"id":"W1483136059","doi":"","title":"Tweet4act: Using Incident-Specific Profiles for Classifying Crisis-Related Messages","year":2013,"lang":"en","type":"article","venue":"","topic":"Public Relations and Crisis Communication","field":"Social Sciences","cited_by":69,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Nautical Research Society","funders":"","keywords":"Incident report; Microblogging; Computer science; Incident response; Social media; Recall; Precision and recall; Preparedness; Period (music); Information retrieval; Artificial intelligence; Data mining; Computer security; World Wide Web","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006949928,0.00008763315,0.0001216838,0.0001163432,0.00109843,0.0003873351,0.0003594249,0.0001419224,0.001348939],"category_scores_gemma":[0.0001232178,0.00007864016,0.00008092188,0.0003584422,0.0001058769,0.001000901,0.00005981729,0.0001122901,0.0001003568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001371186,"about_ca_system_score_gemma":0.000100474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002891653,"about_ca_topic_score_gemma":0.0001496877,"domain_scores_codex":[0.9988406,0.0001645975,0.0002942723,0.0001797801,0.0002416814,0.0002790095],"domain_scores_gemma":[0.9989819,0.0002023882,0.0001410107,0.000304653,0.000280145,0.00008993538],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000004995646,0.0001541049,0.01714671,0.00001517557,0.0000748041,1.995247e-7,0.01452578,0.00008776521,0.00325763,0.8081984,0.111951,0.04458351],"study_design_scores_gemma":[0.001212758,0.00005589866,0.04507882,0.00007151069,0.00007403418,0.00000221155,0.1622767,0.01568278,0.00114904,0.1077746,0.6657108,0.0009108298],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7363369,0.001243921,0.02332671,0.02400317,0.0004734223,0.002049117,0.000004788892,0.0004347982,0.2121272],"genre_scores_gemma":[0.987058,0.0002521349,0.009753216,0.0001155962,0.00007755592,0.0001250461,0.00001429523,0.00001303405,0.002591101],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7004238,"threshold_uncertainty_score":0.999564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.074172964484378,"score_gpt":0.3557708103711271,"score_spread":0.2815978458867491,"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."}}