{"id":"W1978317631","doi":"10.1108/00220410710743306","title":"Machine learning for Asian language text classification","year":2007,"lang":"en","type":"article","venue":"Journal of Documentation","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Text segmentation; Artificial intelligence; Segmentation; Natural language processing; Language model; Support vector machine; Principle of maximum entropy; Market segmentation; Naive Bayes classifier; Word (group theory); Pattern recognition (psychology); Machine learning; Mathematics","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":[0.003723283,0.0007235038,0.0007542802,0.002068666,0.0007288973,0.001656014,0.0007659927,0.000616734,0.004442814],"category_scores_gemma":[0.01080966,0.000197314,0.0007016252,0.003369757,0.000473265,0.002435737,0.0007927918,0.00147845,0.002237157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009990775,"about_ca_system_score_gemma":0.00148201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003238039,"about_ca_topic_score_gemma":0.003307664,"domain_scores_codex":[0.9974582,0.001348121,0.0002016824,0.0003205473,0.0005481025,0.0001233258],"domain_scores_gemma":[0.9936215,0.003933885,0.0005533403,0.0006129617,0.001141553,0.0001366495],"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":[0.0004601218,0.0004213258,0.01726084,0.0006820439,0.0002268114,0.0002492947,0.0003001094,0.06121026,0.007406966,0.01973227,0.01121855,0.8808314],"study_design_scores_gemma":[0.00005778881,0.0003072381,0.008858259,0.0001927038,0.00009288202,0.0002545534,0.0003446789,0.9364767,0.01111862,0.03041082,0.01182401,0.00006171213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1357198,0.005865735,0.8290572,0.002877423,0.0005962008,0.0005887462,0.001813125,0.00469116,0.01879061],"genre_scores_gemma":[0.6385862,0.001729235,0.3508476,0.0004400887,0.0003436882,0.000753201,0.001892652,0.0002035464,0.005203842],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004442814,"threshold_uncertainty_score":0.01969081,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02066179093718157,"score_gpt":0.3197743031696622,"score_spread":0.2991125122324806,"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."}}