{"id":"W2146466957","doi":"10.1109/icmlc.2004.1382026","title":"Combining word based and word co-occurrence based sequence analysis for text categorization","year":2005,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Categorization; Computer science; Word (group theory); Artificial intelligence; Classifier (UML); Text categorization; Curse of dimensionality; Natural language processing; Encoding (memory); Set (abstract data type); Sequence (biology); Data set; Pattern recognition (psychology); 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":[0.00119295,0.0007144766,0.0006746186,0.00381598,0.000459547,0.0008615132,0.0005685223,0.0004638521,0.002447942],"category_scores_gemma":[0.003456464,0.0001862075,0.0005266914,0.003603541,0.0004081622,0.001704162,0.0005263647,0.0004738471,0.002384449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004375031,"about_ca_system_score_gemma":0.0007475537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0030738,"about_ca_topic_score_gemma":0.004895307,"domain_scores_codex":[0.9990656,0.0002336721,0.000093148,0.0002224783,0.0003322769,0.00005283727],"domain_scores_gemma":[0.9985865,0.0005824256,0.0001090121,0.0001240519,0.0005216335,0.00007629691],"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":[0.0002433298,0.0001220182,0.001594758,0.0002977926,0.00009966133,0.00009481434,0.0001565215,0.004991892,0.0564281,0.001729573,0.002013665,0.9322278],"study_design_scores_gemma":[0.00006919579,0.0005898966,0.0085369,0.0001354663,0.0002654953,0.0008547279,0.0003659812,0.8576839,0.0894872,0.0209951,0.02086067,0.0001556519],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03253619,0.0006706958,0.9594708,0.0001335853,0.0002153966,0.0002675581,0.0003942644,0.003242136,0.003069344],"genre_scores_gemma":[0.1496428,0.0004472918,0.8458198,0.00007905295,0.0001140063,0.0001796696,0.0007342685,0.0001353357,0.002847837],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00381598,"threshold_uncertainty_score":0.008189142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04847486091432971,"score_gpt":0.3054395120498646,"score_spread":0.2569646511355348,"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."}}