{"id":"W2604594075","doi":"10.1007/s41347-017-0015-5","title":"Machine Learning for Identifying Emotional Expression in Text: Improving the Accuracy of Established Methods","year":2017,"lang":"en","type":"article","venue":"Journal of Technology in Behavioral Science","topic":"Mental Health via Writing","field":"Psychology","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary; Alberta Health Services","funders":"National Cancer Institute","keywords":"Psychology; Emotional expression; Expressed emotion; Sentence; Contempt; Prosocial behavior; Coding (social sciences); Expression (computer science); Cognitive psychology; Artificial intelligence; Machine learning; Social psychology; Developmental psychology; Computer science","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":[],"consensus_categories":[],"category_scores_codex":[0.006915447,0.0001027062,0.000282694,0.0008882305,0.0005855827,0.00007364268,0.001649612,0.0001571027,0.00004965514],"category_scores_gemma":[0.002887299,0.00007505459,0.00006288892,0.0005232063,0.0007920416,0.0007874047,0.0003837122,0.0009405197,9.346882e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002046589,"about_ca_system_score_gemma":0.0001425915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003313776,"about_ca_topic_score_gemma":0.0000590325,"domain_scores_codex":[0.9980652,0.0001398558,0.0008160017,0.0002435236,0.0003125764,0.0004227795],"domain_scores_gemma":[0.9973413,0.0003129524,0.001718799,0.0003929274,0.0001819664,0.00005208466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00005422475,0.0001379909,0.3415058,0.00001906665,0.000001041789,0.00002155047,0.0004949438,0.0000182238,0.4143885,0.0006139884,0.000004887572,0.2427398],"study_design_scores_gemma":[0.002200572,0.0006285499,0.8909076,0.000773013,0.00002086526,0.0004491135,0.00562129,0.001434079,0.09243738,0.005205449,0.0001360487,0.0001860299],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9939756,0.0004015716,0.003337183,0.00119202,0.0007294935,0.0002720841,0.000001658908,0.00001092072,0.00007940163],"genre_scores_gemma":[0.939348,0.00001136055,0.06054045,0.00001475727,0.0000316687,0.00001963109,2.474025e-7,0.000008132456,0.00002579187],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5494018,"threshold_uncertainty_score":0.4503888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1236501384803663,"score_gpt":0.5167611578015892,"score_spread":0.3931110193212228,"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."}}