{"id":"W3095042565","doi":"10.1007/978-3-030-63128-4_52","title":"Binary Text Representation for Feature Selection","year":2020,"lang":"en","type":"book-chapter","venue":"Advances in intelligent systems and computing","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Redundancy (engineering); Feature selection; Computer science; Binary number; Relevance (law); Minimum redundancy feature selection; Mutual information; Selection (genetic algorithm); Representation (politics); Feature (linguistics); Filter (signal processing); Artificial intelligence; Binary classification; Data mining; Machine learning; Pattern recognition (psychology); Mathematics; Support vector machine","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":[0.000157456,0.0002415725,0.000350166,0.0002180819,0.0001372411,0.0001958439,0.0004137841,0.0002126071,0.000001763675],"category_scores_gemma":[0.00004312126,0.000232687,0.00007282606,0.0001323412,0.00004469114,0.0003900174,0.0002014439,0.0002761439,0.00001094103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008828825,"about_ca_system_score_gemma":0.00002558587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007908388,"about_ca_topic_score_gemma":0.00000512939,"domain_scores_codex":[0.9985129,0.00001885239,0.0004427076,0.0006607088,0.0001845479,0.0001802762],"domain_scores_gemma":[0.9989783,0.0002116195,0.0004182853,0.0002625281,0.00008815948,0.00004116469],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006935306,0.000006421422,0.0001416373,0.0001631446,0.00001456556,0.000002902634,0.0001495959,0.001342855,0.00002891703,0.7801265,0.0007323251,0.2172843],"study_design_scores_gemma":[0.0002517432,0.0002934409,0.00006890617,0.0008241672,0.0000169554,0.00002983405,0.0003003884,0.2796368,0.0004922354,0.07060572,0.6468549,0.0006248682],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0000304396,0.02078483,0.9506171,0.0007470998,0.001234874,0.0009450293,0.000006235769,0.0004737476,0.02516063],"genre_scores_gemma":[0.7319133,0.01648447,0.09569313,0.000502296,0.001852327,0.0003017726,0.0002234528,0.0001988714,0.1528304],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.854924,"threshold_uncertainty_score":0.9488702,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03133614524783514,"score_gpt":0.2986975766940242,"score_spread":0.2673614314461891,"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."}}