{"id":"W2945392980","doi":"10.2196/12383","title":"Flu Outbreak Prediction Using Twitter Posts Classification and Linear Regression With Historical Centers for Disease Control and Prevention Reports: Prediction Framework Study","year":2019,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Outbreak; Computer science; Social media; Control (management); Resource (disambiguation); Disease control; Disease; Disease surveillance; Internet privacy; Machine learning; Data science; Data mining; Environmental health; Artificial intelligence; Medicine; World Wide Web; Virology; Pathology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001106984,0.00023694,0.0005105555,0.000158306,0.0002114222,0.00006721745,0.00003945482,0.000114761,0.000005495937],"category_scores_gemma":[0.00035054,0.0001870206,0.00004421979,0.0001960992,0.00006337421,0.0003254166,0.00003397728,0.0002143877,5.236907e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003767873,"about_ca_system_score_gemma":0.0004235994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004328615,"about_ca_topic_score_gemma":0.00001494211,"domain_scores_codex":[0.9975252,0.000300804,0.0006036075,0.0007725055,0.0004029789,0.0003948712],"domain_scores_gemma":[0.9978057,0.0001366317,0.0004341083,0.000477191,0.0002481188,0.0008982793],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001808206,0.0003576278,0.9905373,0.0006070466,0.00005391824,0.000009344495,0.0003227233,0.000002344319,0.00005152273,0.000008738189,0.0009216969,0.005319517],"study_design_scores_gemma":[0.00362078,0.001585034,0.9645374,0.000237121,0.00001538207,0.00006518753,0.0003317782,0.02078905,1.146403e-7,0.00002680471,0.00864071,0.0001506398],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9799759,0.001088074,0.009778348,0.003908231,0.0003608286,0.004504237,0.0002176239,0.0001530126,0.00001378287],"genre_scores_gemma":[0.9971858,0.0001644762,0.0007696374,0.0006437918,0.0002291572,0.0002511026,0.0005672073,0.00003606786,0.0001527417],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02599991,"threshold_uncertainty_score":0.762648,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03905220092828261,"score_gpt":0.3329857680524992,"score_spread":0.2939335671242166,"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."}}