{"id":"W4281894768","doi":"10.1016/j.jbusres.2022.05.078","title":"Predicting social media engagement with computer vision: An examination of food marketing on Instagram","year":2022,"lang":"en","type":"article","venue":"Journal of Business Research","topic":"Digital Marketing and Social Media","field":"Social Sciences","cited_by":76,"is_retracted":false,"has_abstract":true,"ca_institutions":"Saint Mary's University; Toronto Metropolitan University","funders":"","keywords":"Social media; Product (mathematics); Customer engagement; Advertising; Social media marketing; Marketing; User engagement; Proxy (statistics); Affect (linguistics); Process (computing); Business; Psychology; Computer science; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"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":["sts"],"consensus_categories":[],"category_scores_codex":[0.02640948,0.00007868317,0.0002206496,0.0004372897,0.001502461,0.000161576,0.0004308066,0.00005064474,0.00009978557],"category_scores_gemma":[0.00379401,0.00006813632,0.00005064534,0.001397363,0.0003281233,0.0004016619,0.0001701562,0.0007428324,5.683726e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002909069,"about_ca_system_score_gemma":0.0005740043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004488779,"about_ca_topic_score_gemma":0.0001356018,"domain_scores_codex":[0.9910733,0.004655533,0.0003879273,0.0001472441,0.003398457,0.0003375984],"domain_scores_gemma":[0.9950175,0.002716939,0.0003706458,0.00008310381,0.001691936,0.0001199305],"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":[0.001694203,0.001250162,0.005518559,0.000130762,0.00008809412,0.0001014876,0.09860449,0.0005500431,0.0001729405,0.00315474,0.001150366,0.8875841],"study_design_scores_gemma":[0.001821732,0.003994956,0.8367168,0.0004687252,0.00002673667,0.00001376961,0.1433384,0.0004704354,0.00004313892,0.0006892971,0.01214446,0.0002715302],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9845839,0.00002680161,0.00004367633,0.0009246395,0.0004722166,0.000154596,0.000006563881,0.00001374971,0.0137739],"genre_scores_gemma":[0.9982185,0.00002487811,0.0002619624,0.00001810899,0.001394696,0.000007763917,0.000003495129,0.00001446766,0.00005611598],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8873127,"threshold_uncertainty_score":0.9997975,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09979534631881372,"score_gpt":0.3777658877577635,"score_spread":0.2779705414389498,"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."}}