{"id":"W4399205224","doi":"10.1609/icwsm.v18i1.31324","title":"Reliability Analysis of Psychological Concept Extraction and Classification in User-Penned Text","year":2024,"lang":"en","type":"article","venue":"Proceedings of the International AAAI Conference on Web and Social Media","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute","funders":"National Institute on Aging; National Institutes of Health","keywords":"Witness; Task (project management); Reliability (semiconductor); Perception; Focus (optics); Computer science; Cognitive psychology; Social media; Psychology; Binary classification; Deep learning; Artificial intelligence; Natural language processing; Data 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":[],"consensus_categories":[],"category_scores_codex":[0.0003258112,0.00006295455,0.0001419326,0.000154341,0.00002849353,0.00008214251,0.0003447634,0.0000661154,0.00001619319],"category_scores_gemma":[0.0002194401,0.00004619969,0.00004843226,0.0002847115,0.0001137328,0.0002445396,0.00008828973,0.0001402915,5.232305e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003250892,"about_ca_system_score_gemma":0.00002504174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001224656,"about_ca_topic_score_gemma":0.00001636129,"domain_scores_codex":[0.9991588,0.00001098438,0.0002370385,0.0002605572,0.00026675,0.00006587435],"domain_scores_gemma":[0.9994763,0.0001611121,0.0001097365,0.00005144484,0.0001826823,0.00001869712],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00002570173,0.0000739277,0.01222681,0.00002630466,0.00005864134,2.657143e-7,0.005285631,0.00001005371,0.02467186,0.918659,0.00007367997,0.03888813],"study_design_scores_gemma":[0.0002613956,0.0000417515,0.5350537,0.0001054047,0.00005664798,0.000001791719,0.0009297315,0.4224719,0.001224411,0.03945658,0.0002786169,0.0001180696],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9922996,0.00002603583,0.0008882636,0.004445446,0.0002871242,0.00006975717,0.000006655115,0.00001831892,0.001958754],"genre_scores_gemma":[0.9989897,0.00005695549,0.0008109088,0.00004579579,0.00004228793,0.000007645644,0.000001309156,0.000001762495,0.00004363598],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8792024,"threshold_uncertainty_score":0.1883969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06272372588259084,"score_gpt":0.3327324522235726,"score_spread":0.2700087263409817,"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."}}