{"id":"W4404682082","doi":"10.54254/2755-2721/97/20241397","title":"Review on Application of Chi-square Statistic in Text Classification in Recent Five Years","year":2024,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Feature selection; Statistic; Chi-square test; Computer science; Feature (linguistics); Selection (genetic algorithm); Test (biology); Natural language processing; Artificial intelligence; Information retrieval; Statistics; Mathematics; Linguistics","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":[0.0001288408,0.00007422196,0.0001087876,0.0002341128,0.000008982805,0.00002883132,0.0001426737,0.00003176621,0.000002288212],"category_scores_gemma":[0.00001802634,0.00007696576,0.00001144931,0.0005934669,0.00001391623,0.00008585915,0.00003323239,0.0001014775,0.00001165635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005094354,"about_ca_system_score_gemma":0.00002411845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004684353,"about_ca_topic_score_gemma":0.000001234118,"domain_scores_codex":[0.9993276,0.00000665186,0.0002335122,0.0002292877,0.0001209031,0.00008202058],"domain_scores_gemma":[0.9996813,0.0001254728,0.00003829031,0.0001221267,0.00001654003,0.00001625475],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001301298,0.00001848506,0.00003086195,0.0002554516,0.000002729908,8.09134e-7,0.00009904629,0.02509805,0.0002022745,0.6940728,0.00006789729,0.2801503],"study_design_scores_gemma":[0.0001579576,0.00002109756,0.05105744,0.0005965101,0.000002543401,0.000001709156,0.00003186229,0.9249608,0.00008280116,0.01968819,0.003274437,0.000124649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009232354,0.004682334,0.9836602,0.001271766,0.00006677015,0.000445993,0.000005797058,0.0002392313,0.0003955237],"genre_scores_gemma":[0.9866948,0.001372448,0.01175452,0.00007530696,0.000006277173,0.00006244405,0.00002425858,0.000005559088,0.000004448708],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9774624,"threshold_uncertainty_score":0.3138573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01252962739796657,"score_gpt":0.2512400210169778,"score_spread":0.2387103936190112,"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."}}