{"id":"W4392200058","doi":"10.18280/isi.290118","title":"Labeling Consistency Test of Multi-Label Data for Aspect and Sentiment Classification Using the Cohen Kappa Method","year":2024,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Data Mining and Machine Learning Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Universitas Diponegoro","keywords":"Kappa; Consistency (knowledge bases); Computer science; Class (philosophy); Artificial intelligence; Process (computing); Labeled data; Cohen's kappa; Test data; Data mining; Machine learning; Pattern recognition (psychology); Natural language processing; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1075947,0.001081922,0.001932816,0.007526543,0.004702542,0.00368848,0.002206941,0.00224884,0.003237905],"category_scores_gemma":[0.2975633,0.0006885244,0.003014703,0.005462592,0.003473367,0.004226808,0.003104067,0.002050954,0.0006136034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002289907,"about_ca_system_score_gemma":0.002778494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002926105,"about_ca_topic_score_gemma":0.003020434,"domain_scores_codex":[0.8730429,0.06134465,0.01936981,0.01586702,0.02833027,0.002045358],"domain_scores_gemma":[0.5141079,0.3522165,0.02403746,0.02332264,0.08400193,0.002313505],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005166257,0.0009225724,0.5295679,0.003929216,0.005353719,0.0009688367,0.02136462,0.01068801,0.01646819,0.02361913,0.01480637,0.3671451],"study_design_scores_gemma":[0.0009208255,0.004538959,0.5527858,0.002109387,0.003931594,0.002731232,0.0386631,0.241353,0.04076593,0.07488348,0.03594414,0.001372587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5505012,0.001962835,0.41242,0.001116751,0.001474956,0.003602381,0.002079693,0.0009873052,0.02585482],"genre_scores_gemma":[0.8850372,0.0002194896,0.1094045,0.0002030386,0.0001824578,0.002407496,0.001090838,0.0001813666,0.001273688],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1075947,"threshold_uncertainty_score":0.5690222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08785438586259763,"score_gpt":0.3523426165322655,"score_spread":0.2644882306696679,"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."}}