{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009179532,0.0006986194,0.0004756412,0.005183544,0.000715411,0.001941134,0.0008824621,0.001141585,0.002730541],"category_scores_gemma":[0.09201656,0.0002497089,0.000759215,0.00271893,0.0009337461,0.003104231,0.002008622,0.001612082,0.001629192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007811617,"about_ca_system_score_gemma":0.0005751084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00219723,"about_ca_topic_score_gemma":0.002233544,"domain_scores_codex":[0.9933777,0.002814072,0.0007826257,0.001163801,0.001609325,0.0002524814],"domain_scores_gemma":[0.871254,0.1072158,0.006013283,0.006221525,0.00845799,0.0008374373],"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":[0.002898385,0.0008902985,0.4267865,0.002785094,0.000539618,0.001364253,0.01864663,0.01960298,0.02951862,0.0102727,0.02851801,0.458177],"study_design_scores_gemma":[0.0001245728,0.0006452183,0.3525974,0.0002986588,0.0002645761,0.001052826,0.005540395,0.564326,0.02973239,0.01897549,0.02622245,0.0002199374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8695698,0.0008641017,0.10961,0.001070361,0.0001942161,0.0003841323,0.01087839,0.002847628,0.004581323],"genre_scores_gemma":[0.9472046,0.0001364716,0.03931013,0.00009779628,0.0001371435,0.0003662205,0.01145539,0.0001544245,0.001137696],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009179532,"threshold_uncertainty_score":0.04854661,"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."}}