{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01083795,0.001020101,0.002122804,0.009132147,0.000605258,0.002227946,0.002205756,0.001375593,0.002487849],"category_scores_gemma":[0.03799849,0.0005482835,0.001731503,0.01208761,0.001871795,0.002803733,0.0007926535,0.001878253,0.001397811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001743246,"about_ca_system_score_gemma":0.004060589,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005369814,"about_ca_topic_score_gemma":0.004951788,"domain_scores_codex":[0.9905318,0.003863971,0.001476871,0.001081147,0.002890097,0.0001560804],"domain_scores_gemma":[0.925755,0.0607085,0.002630023,0.0008561371,0.009691757,0.0003585069],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0001390984,0.00005446136,0.006171899,0.01874417,0.0003750115,0.0001493706,0.0003976031,0.001001178,0.0007623368,0.006034901,0.01707758,0.9490925],"study_design_scores_gemma":[0.00007570523,0.0007514357,0.039932,0.02773399,0.001601521,0.003341322,0.001829926,0.009314071,0.005833663,0.02394993,0.8852174,0.0004189088],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00170995,0.9738722,0.01730104,0.002777231,0.0009681492,0.00006604181,0.0002120464,0.0001190088,0.002974295],"genre_scores_gemma":[0.02593046,0.9454756,0.02302913,0.001303779,0.002543941,0.0002104199,0.0005566967,0.00006608331,0.0008838522],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.989162,"threshold_uncertainty_score":0.05731726,"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."}}