{"id":"W3027106232","doi":"10.1016/s2352-4642(20)30101-2","title":"Leveraging artificial intelligence to monitor unhealthy food and brand marketing to children on digital media","year":2020,"lang":"en","type":"article","venue":"The Lancet Child & Adolescent Health","topic":"Obesity, Physical Activity, Diet","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"Canadian Institutes of Health Research","keywords":"Unhealthy food; Scopus; Food marketing; Advertising; Digital advertising; Appeal; Consumption (sociology); Marketing; Psychology; Medicine; Digital marketing; MEDLINE; Business; Social media marketing; Political science; Sociology; Obesity; Social science","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005629648,0.0002739796,0.0006621188,0.00006761575,0.0002952341,0.00009761628,0.0002505078,0.00004606649,0.000008972438],"category_scores_gemma":[0.0004683097,0.0002073902,0.00007102218,0.0003194049,0.00005824292,0.00007981035,0.000235477,0.0009607251,0.0001075699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001297934,"about_ca_system_score_gemma":0.00007129501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004079584,"about_ca_topic_score_gemma":0.000030452,"domain_scores_codex":[0.9976569,0.0001810624,0.0003856229,0.0005737836,0.0004940575,0.0007085059],"domain_scores_gemma":[0.9982376,0.0002250669,0.0001139638,0.0003879493,0.00004167041,0.0009937779],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.007560067,0.005713195,0.3143409,0.001597772,0.0001963852,0.00001686586,0.01405309,0.000221847,0.000137167,0.002146614,0.01305972,0.6409563],"study_design_scores_gemma":[0.0003983401,0.001244571,0.9952081,0.0009096876,0.00001971621,0.00001652731,0.0002340532,0.0002136738,0.0006089925,0.0003717273,0.0005348921,0.0002396472],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8111129,0.0001516627,0.0003100136,0.1866236,0.000176061,0.001168776,0.00008581096,0.0001264219,0.0002447861],"genre_scores_gemma":[0.9448069,0.00009123886,0.0001517005,0.04899704,0.005880079,0.000008058563,0.00002152613,0.00004133969,0.000002158166],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6808672,"threshold_uncertainty_score":0.8457125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04907154364508422,"score_gpt":0.3006910094343633,"score_spread":0.2516194657892791,"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."}}