{"id":"W4293574685","doi":"10.2196/37862","title":"Search Term Identification Methods for Computational Health Communication: Word Embedding and Network Approach for Health Content on YouTube","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Cancer Institute; National Institutes of Health","keywords":"Computer science; Information retrieval; Social media; Word embedding; Relevance (law); Health communication; Misinformation; Identification (biology); Natural language processing; Artificial intelligence; World Wide Web; Embedding","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":[0.001662727,0.001134998,0.000888258,0.007627451,0.0007252085,0.001172155,0.001112026,0.001343929,0.003240966],"category_scores_gemma":[0.01092974,0.0002390661,0.001012618,0.004858144,0.0004617911,0.002624532,0.001108917,0.001093708,0.001306662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001710028,"about_ca_system_score_gemma":0.0009704632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01890694,"about_ca_topic_score_gemma":0.01945367,"domain_scores_codex":[0.998804,0.0005105009,0.0001574581,0.000231574,0.000201999,0.00009447758],"domain_scores_gemma":[0.9948251,0.004035738,0.000303803,0.0002158068,0.0005357488,0.00008375253],"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":[0.001321859,0.0007491422,0.01647161,0.001916365,0.0003453132,0.0009136622,0.001425269,0.1038172,0.01056315,0.02150863,0.02920294,0.8117648],"study_design_scores_gemma":[0.00004091661,0.00009611457,0.002311315,0.00005109204,0.00004245433,0.0001478861,0.0003696725,0.9839877,0.001617063,0.008101218,0.003210028,0.00002451704],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2818398,0.006963451,0.6829939,0.003266941,0.0003842194,0.00139476,0.01167794,0.003862019,0.007616931],"genre_scores_gemma":[0.6119502,0.001661693,0.3635291,0.0003276941,0.0003268772,0.001396935,0.01306365,0.0002177061,0.0075261],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01890694,"threshold_uncertainty_score":0.03759378,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1266566128726909,"score_gpt":0.4513652831696563,"score_spread":0.3247086702969654,"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."}}