{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002529034,0.0001327508,0.0001691289,0.0003861756,0.0001771439,0.000280405,0.0005552862,0.00006976265,0.00004727966],"category_scores_gemma":[0.00009013528,0.0001198461,0.00006308099,0.001228871,0.0000851532,0.0005802254,0.00005141426,0.00007015352,0.00001336823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004832964,"about_ca_system_score_gemma":0.00007870943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001048686,"about_ca_topic_score_gemma":0.00002359358,"domain_scores_codex":[0.9988844,0.00002758966,0.000242608,0.0004378204,0.0001853711,0.0002221921],"domain_scores_gemma":[0.9989702,0.0002488643,0.0001331459,0.0004886176,0.00009779944,0.00006143854],"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":[0.00002436149,0.0001976543,0.05047381,0.00004186479,0.0000957683,0.000001331769,0.0002907389,0.008154235,0.003169195,0.2051049,0.002524104,0.7299221],"study_design_scores_gemma":[0.0004750357,0.00004427882,0.005301156,0.000006375854,0.00003656691,3.018154e-7,0.00004621128,0.9679119,0.01663797,0.001238038,0.008076507,0.0002256611],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007900533,0.00002747453,0.9856416,0.005238493,0.0000416526,0.0002077368,0.00001342889,0.000594172,0.0003348898],"genre_scores_gemma":[0.8775806,0.000005808798,0.1216055,0.0004892413,0.000008471085,0.00006558697,0.00007282985,0.000003295408,0.0001686185],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9597577,"threshold_uncertainty_score":0.4887183,"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."}}