{"id":"W2106388373","doi":"10.1016/j.ipm.2006.07.006","title":"Contextual feature selection for text classification","year":2006,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bigram; Computer science; Feature selection; Selection (genetic algorithm); Set (abstract data type); Filter (signal processing); Feature (linguistics); Information retrieval; Artificial intelligence; Data set; Simple (philosophy); Data mining","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002119197,0.0001242126,0.00008759966,0.0002985961,0.0003129859,0.0007585027,0.0004569902,0.00007986478,0.000004744578],"category_scores_gemma":[0.0000169741,0.000116957,0.00004045977,0.0005321605,0.00003147667,0.003606564,0.00007274961,0.0000726302,0.00007328501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001135724,"about_ca_system_score_gemma":0.00002842137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004926117,"about_ca_topic_score_gemma":0.00000290776,"domain_scores_codex":[0.9990277,0.000009441575,0.000320624,0.000185944,0.0002538463,0.0002024165],"domain_scores_gemma":[0.9992192,0.00001722092,0.0003003244,0.0002337918,0.0002090713,0.00002035495],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005299148,0.00002154999,0.00006723826,0.00007507172,0.000004753474,4.280996e-8,0.00009465446,0.00008718928,0.00008632907,0.405114,0.02218106,0.5722628],"study_design_scores_gemma":[0.0009453513,0.00005582329,0.02061323,0.00004525199,0.0000187537,0.000004343916,0.0006796308,0.2236008,0.002159437,0.03635827,0.715178,0.0003411766],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005657965,0.00004761372,0.9747341,0.003883165,0.0001336529,0.0005448034,0.000001902325,0.00104335,0.01904564],"genre_scores_gemma":[0.9032106,0.000007654725,0.09319261,0.0003962839,0.00004024611,0.000353814,0.00007857781,0.000005585226,0.00271464],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9026448,"threshold_uncertainty_score":0.7314259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01355166644046986,"score_gpt":0.2484269728550914,"score_spread":0.2348753064146216,"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."}}