{"id":"W2715985536","doi":"10.2196/publichealth.6577","title":"Filtering Entities to Optimize Identification of Adverse Drug Reaction From Social Media: How Can the Number of Words Between Entities in the Messages Help?","year":2017,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Pharmacovigilance and Adverse Drug Reactions","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Popularity; False positive paradox; Term (time); Social media; Recall; Drug; Computer science; Medicine; Information retrieval; Psychiatry; Psychology; Machine learning; Cognitive psychology; World Wide Web; Social psychology","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":[0.006735983,0.001574758,0.001451548,0.008250163,0.000934829,0.002619107,0.000846631,0.001579144,0.001368904],"category_scores_gemma":[0.02444519,0.0003828506,0.00104886,0.002345097,0.0005723494,0.002946803,0.001005366,0.001164496,0.00165573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009218091,"about_ca_system_score_gemma":0.001063451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006980014,"about_ca_topic_score_gemma":0.009859618,"domain_scores_codex":[0.9959095,0.001573034,0.0004581781,0.0009620816,0.0008466537,0.0002507025],"domain_scores_gemma":[0.9800238,0.01484225,0.001917536,0.0008850901,0.001987745,0.0003435855],"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":[0.001342415,0.000740158,0.3281124,0.001595993,0.0007904569,0.0006793893,0.001764007,0.007020884,0.03139699,0.002067986,0.01329072,0.6111986],"study_design_scores_gemma":[0.0002057029,0.001056384,0.4601951,0.0006417301,0.001142118,0.002732804,0.003014707,0.4390123,0.05424905,0.009146599,0.02831037,0.0002930819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7828795,0.007033535,0.1884125,0.003679984,0.0004922492,0.0009492655,0.005466739,0.003567212,0.007519084],"genre_scores_gemma":[0.8465996,0.001065667,0.1445201,0.0003950215,0.0003196932,0.0002059812,0.004332333,0.0001296242,0.002431904],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.008250163,"threshold_uncertainty_score":0.03562367,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1290499107859054,"score_gpt":0.437439936973234,"score_spread":0.3083900261873286,"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."}}