{"id":"W4285364837","doi":"10.2196/33678","title":"Classification of Twitter Vaping Discourse Using BERTweet: Comparative Deep Learning Study","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine; National Cancer Institute; National Institutes of Health; National Science Foundation","keywords":"Computer science; Artificial intelligence; Deep learning; Machine learning; Relevance (law); Classifier (UML); Sentiment analysis; Random forest; Natural language processing; Language model; Transfer of learning; Transformer; Information retrieval","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001694497,0.0007583582,0.0004351365,0.001905915,0.0004226179,0.001109005,0.0008222759,0.0009711097,0.001933273],"category_scores_gemma":[0.005851564,0.0001769817,0.0005558939,0.001166666,0.0004582358,0.002232384,0.0009556868,0.001347571,0.000986106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001237218,"about_ca_system_score_gemma":0.0005169489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01266736,"about_ca_topic_score_gemma":0.0152312,"domain_scores_codex":[0.9993487,0.0002326974,0.0000450849,0.0001406332,0.0001279027,0.0001049648],"domain_scores_gemma":[0.997183,0.001774999,0.0001979091,0.0002024495,0.0005201552,0.0001215444],"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":[0.002190085,0.002486455,0.2696718,0.0009004297,0.000521245,0.0008160758,0.002970261,0.08011302,0.009180678,0.003646271,0.03060834,0.5968953],"study_design_scores_gemma":[0.00003633223,0.0004646321,0.07539706,0.0001377839,0.00008492246,0.0001515045,0.002860563,0.9088029,0.004765164,0.002488235,0.00474885,0.00006198241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.983242,0.001108014,0.00854235,0.0006162939,0.0001219898,0.00008688655,0.001702504,0.0002806873,0.004299158],"genre_scores_gemma":[0.9869837,0.0004141467,0.005657719,0.0001065894,0.00006059019,0.00004950663,0.004049102,0.0000406472,0.002637969],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01266736,"threshold_uncertainty_score":0.02518725,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07220711212445817,"score_gpt":0.3981763846864982,"score_spread":0.32596927256204,"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."}}