{"id":"W4390202391","doi":"10.2196/54369","title":"Capacity of Generative AI to Interpret Human Emotions From Visual and Textual Data: Pilot Evaluation Study","year":2023,"lang":"en","type":"article","venue":"JMIR Mental Health","topic":"Mental Health via Writing","field":"Psychology","cited_by":118,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Mentalization; Psychology; Cognitive psychology; Theory of mind; Comprehension; Cognition; Developmental psychology; Computer science","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":[0.00160415,0.0001631383,0.0003069955,0.0001873194,0.0004136192,0.0000215881,0.0002113476,0.00004348796,0.0005860659],"category_scores_gemma":[0.00002977122,0.0001722985,0.00001684384,0.0003323338,0.00006522666,0.0001484241,0.00034035,0.0002149836,0.0002682071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003162753,"about_ca_system_score_gemma":0.0001105557,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01484579,"about_ca_topic_score_gemma":0.006577864,"domain_scores_codex":[0.996944,0.0009492914,0.0006249893,0.0006307147,0.0004658623,0.0003851618],"domain_scores_gemma":[0.9989399,0.000115045,0.0001458709,0.0004714674,0.00005136988,0.0002763765],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.001338864,0.01220054,0.1494642,0.0004192873,0.0004261427,0.00002052377,0.5353467,0.000008926017,0.01832894,0.003771894,0.1300059,0.1486681],"study_design_scores_gemma":[0.003599924,0.01066398,0.8891531,0.0002135436,0.00002402071,0.000009010862,0.09384201,0.001432165,0.0001932463,0.0004102357,0.0002050914,0.0002537231],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9919844,0.00004699184,0.00003064629,0.001780386,0.0005034507,0.003673594,0.001290408,0.00007718484,0.0006129589],"genre_scores_gemma":[0.9958608,0.000003393743,0.0001378376,0.001797619,0.0001786884,0.0003263148,0.001542325,0.00002418111,0.0001288072],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7396888,"threshold_uncertainty_score":0.9917144,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2293141211726353,"score_gpt":0.5418588110602662,"score_spread":0.312544689887631,"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."}}