{"id":"W167522204","doi":"","title":"Beyond TFIDF weighting for text categorization in the vector space model","year":2005,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":232,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Weighting; tf–idf; Vector space model; Computer science; Artificial intelligence; Categorization; Leverage (statistics); Vocabulary; Feature selection; Support vector machine; Text categorization; Word (group theory); Feature vector; Natural language processing; Machine learning; Information retrieval; Pattern recognition (psychology); Mathematics; Term (time)","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":[0.0002106247,0.00006599649,0.00005621601,0.00008115535,0.00008920509,0.0001416229,0.0006710455,0.00004463021,0.000006933611],"category_scores_gemma":[0.0000449408,0.00004333883,0.00002352552,0.0003019319,0.00001850894,0.0004982087,0.00006211383,0.00005728816,0.00002748181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003424355,"about_ca_system_score_gemma":0.00002650696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006283191,"about_ca_topic_score_gemma":0.00003636875,"domain_scores_codex":[0.9993961,0.00001243511,0.0001325906,0.0001889467,0.0001184198,0.000151468],"domain_scores_gemma":[0.9994859,0.00008719326,0.00004969614,0.0003340742,0.00003152157,0.0000116317],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[7.459707e-7,0.00002172111,0.00007295346,0.000001860438,8.531248e-7,6.24086e-8,0.0005590461,0.001026591,0.0007926935,0.9607506,0.002867666,0.03390522],"study_design_scores_gemma":[0.0001683387,0.00001756063,0.0003313762,0.000001615209,0.000001216206,7.247457e-7,0.0001856786,0.9080166,0.008270115,0.07531867,0.007604068,0.00008408588],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003784743,0.00003793399,0.9500412,0.03656249,0.00004376234,0.0002222862,4.619872e-7,0.000250612,0.00905655],"genre_scores_gemma":[0.8762227,0.000007246621,0.1216634,0.0004539123,0.00003058514,0.00006506559,0.000002120652,0.000003244042,0.001551685],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9069899,"threshold_uncertainty_score":0.1767306,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02088681033409115,"score_gpt":0.2605201725384578,"score_spread":0.2396333622043666,"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."}}