{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001348836,0.0001049136,0.0001270133,0.0001286682,0.0003482934,0.0004926827,0.0005756801,0.00004482142,0.000001166969],"category_scores_gemma":[0.0005598589,0.00008161839,0.00001937812,0.0003597396,0.00009226314,0.001988717,0.0002885514,0.0001025814,0.000006531004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005721872,"about_ca_system_score_gemma":0.000121317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009636152,"about_ca_topic_score_gemma":0.000004356448,"domain_scores_codex":[0.9990108,0.00005697263,0.0004304181,0.000211686,0.0001481006,0.000142027],"domain_scores_gemma":[0.9982783,0.0005979587,0.0002203002,0.0007113726,0.0001591337,0.00003293333],"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":[0.000004975451,0.00005464034,0.0003394976,0.0007103482,0.00009521963,3.501549e-7,0.007537483,0.0005399381,0.009787137,0.09624207,0.0009300665,0.8837582],"study_design_scores_gemma":[0.0001756234,0.00003442798,0.0004018937,0.0001377115,0.00004438519,0.00002865811,0.0004675911,0.9925012,0.0003959682,0.001220511,0.004497693,0.00009433585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002890456,0.00044898,0.9951063,0.0003577989,0.0001436814,0.0003976805,0.0002058409,0.0001529936,0.0002962423],"genre_scores_gemma":[0.2975594,0.00002596056,0.701919,0.00006438139,0.00002793317,0.00005256318,0.0003133638,0.000007630127,0.00002983445],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9919612,"threshold_uncertainty_score":0.4750951,"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."}}