{"id":"W3151875318","doi":"10.2196/23305","title":"Effective Training Data Extraction Method to Improve Influenza Outbreak Prediction from Online News Articles: Deep Learning Model Study","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Research Foundation of Korea; National Research Foundation","keywords":"Computer science; Word embedding; Machine learning; Artificial intelligence; Microblogging; Social media; Data mining; Word (group theory); Embedding; World Wide Web","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001263736,0.0002887989,0.0006535595,0.0001476492,0.0001264748,0.00008363624,0.000371024,0.0002260288,0.0001956234],"category_scores_gemma":[0.004695175,0.0002593937,0.00008952492,0.0005123754,0.00005529757,0.0008916619,0.0006537087,0.001045848,0.0001115006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001781366,"about_ca_system_score_gemma":0.0004872541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009739168,"about_ca_topic_score_gemma":0.000274974,"domain_scores_codex":[0.9961749,0.0003181065,0.001191493,0.0004453626,0.001431295,0.000438882],"domain_scores_gemma":[0.9966605,0.0005906919,0.0003695419,0.00118373,0.0002971945,0.0008983445],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005038719,0.001553168,0.02262369,0.0002072116,0.0004605131,0.0001391102,0.03317444,0.003614858,0.00105537,0.000007841502,0.001102555,0.9355574],"study_design_scores_gemma":[0.003879358,0.0004931926,0.04915855,0.000268519,0.0002751806,0.00004528786,0.04211156,0.8981028,0.0001533072,0.0000541303,0.005211979,0.0002461643],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7018592,0.00005322445,0.2947833,0.0002571131,0.0002164688,0.001371136,0.0007572452,0.000327734,0.0003745983],"genre_scores_gemma":[0.8345941,0.00002781236,0.1520344,0.005904194,0.0008945276,0.0003287045,0.0060224,0.00007853893,0.0001153602],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9353112,"threshold_uncertainty_score":0.9999858,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05695722559282902,"score_gpt":0.4006417169882084,"score_spread":0.3436844913953794,"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."}}