{"id":"W4296139443","doi":"10.1007/978-3-031-17114-7_23","title":"Automated Utterance Labeling of Conversations Using Natural Language Processing","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Mental Health via Writing","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University; University of British Columbia","funders":"","keywords":"Computer science; Utterance; Artificial intelligence; Python (programming language); Natural language processing; Domain adaptation; Task (project management); Context (archaeology); Classifier (UML); Programming language","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":[0.00058613,0.0002534928,0.000361022,0.0004938575,0.0003067872,0.00005153091,0.0006198141,0.000138453,0.0004060255],"category_scores_gemma":[0.00003941898,0.0002688431,0.00005491893,0.0004384648,0.0003797243,0.0001759187,0.0003013776,0.0007884706,0.000009273756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003912599,"about_ca_system_score_gemma":0.0003065213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002182233,"about_ca_topic_score_gemma":0.00004514873,"domain_scores_codex":[0.9977583,0.00005295653,0.0005237163,0.0006900812,0.0005249036,0.0004500943],"domain_scores_gemma":[0.998723,0.0002665636,0.0004381479,0.000403494,0.000105432,0.00006340695],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005579129,0.00008937918,0.001143275,0.0008798484,0.00003722417,0.0003143488,0.03355473,0.03730778,0.007377891,0.002396043,0.00001998929,0.9168237],"study_design_scores_gemma":[0.0005991071,0.00009512057,0.0003515019,0.001236443,0.00002127497,0.0001770025,0.00002546134,0.994985,0.0008718414,0.000916301,0.0001903855,0.0005304867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1214207,0.02094616,0.8241938,0.0008122943,0.01336718,0.002506889,0.0001243457,0.00121686,0.01541172],"genre_scores_gemma":[0.9027283,0.000002991767,0.09592839,0.0009184086,0.0002097471,0.00000710533,0.00001626461,0.00003780355,0.0001510113],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9576773,"threshold_uncertainty_score":0.9999764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0318175748855377,"score_gpt":0.3563982541969533,"score_spread":0.3245806793114155,"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."}}