{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005970232,0.0001138168,0.0003076034,0.0001359722,0.001132386,0.0001967916,0.0006909358,0.00003908308,0.00001387071],"category_scores_gemma":[0.0000617978,0.0001053587,0.00009126205,0.0003575855,0.00005844804,0.0002543945,0.0003933964,0.0002540609,0.000001020053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000152217,"about_ca_system_score_gemma":0.0002794192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004700545,"about_ca_topic_score_gemma":4.78063e-7,"domain_scores_codex":[0.9975704,0.000330004,0.0009264495,0.0001787355,0.0006609209,0.0003335069],"domain_scores_gemma":[0.9980826,0.0007474609,0.0004538678,0.0003706113,0.0001096662,0.0002357818],"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":[0.00004572073,0.0002709439,0.0002761229,0.0004240148,0.0001180152,8.285179e-8,0.02490851,0.05523714,6.689968e-7,0.09954457,0.02709135,0.7920828],"study_design_scores_gemma":[0.0006693872,0.0001975267,0.0004313305,0.00004069557,0.000003748955,0.000005587873,0.002438553,0.9885709,0.000001724542,0.0006552786,0.006885674,0.00009962145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007689413,0.0003194834,0.9899454,0.007668952,0.0001620589,0.001013384,0.00001209487,0.00005464283,0.0000550679],"genre_scores_gemma":[0.01968473,0.00006569741,0.9714935,0.007286197,0.00008966785,0.0006154212,0.0006818976,0.000009567194,0.00007327213],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9333338,"threshold_uncertainty_score":0.8709511,"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."}}