{"id":"W3122456778","doi":"10.1101/2021.01.16.21249943","title":"Artificial Intelligence for Emotion-Semantic Trending and People Emotion Detection During COVID-19 Social Isolation","year":2021,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Mental Health via Writing","field":"Psychology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Feeling; Disgust; Novelty; Sentiment analysis; Anticipation (artificial intelligence); Emotion detection; Psychology; Loneliness; Social media; Anger; Isolation (microbiology); Semantics (computer science); Emotion classification; Cognitive psychology; Social psychology; Computer science; Artificial intelligence; Emotion recognition; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001022579,0.0002766443,0.0003948325,0.0003132672,0.0009140478,0.0001417294,0.0001308449,0.0004622618,0.0003213704],"category_scores_gemma":[0.0003846356,0.0003506654,0.0001454822,0.000252717,0.00005131226,0.000107565,0.0001898313,0.000536016,0.00002067206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004644885,"about_ca_system_score_gemma":0.00009064601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004245622,"about_ca_topic_score_gemma":0.001231192,"domain_scores_codex":[0.9972943,0.000366415,0.0007926577,0.0008735837,0.0002253069,0.0004477357],"domain_scores_gemma":[0.998722,0.0002850846,0.0004780212,0.0002609646,0.00008163756,0.000172349],"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":[0.001681889,0.001046778,0.2374624,0.02338172,0.0005175907,0.0001032364,0.2082523,0.001384238,0.06220622,0.009257359,0.00008291427,0.4546233],"study_design_scores_gemma":[0.001084893,0.0003484234,0.8486613,0.0008605146,0.0004125472,0.0002666404,0.05656895,0.05472399,0.01728338,0.01794136,0.0000984929,0.001749461],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7438849,0.0001130111,0.2518765,0.0006763551,0.002461783,0.0007429753,0.00002017176,0.0001263772,0.00009795463],"genre_scores_gemma":[0.9974318,0.00002589415,0.000657246,0.000093297,0.001210453,0.0002758978,0.0001605421,0.00005375781,0.00009109016],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6111989,"threshold_uncertainty_score":0.9998946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0939238861364869,"score_gpt":0.3969084391771672,"score_spread":0.3029845530406803,"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."}}