{"id":"W2151849342","doi":"10.1109/hicss.2003.1174243","title":"Support vector machines for text categorization","year":2003,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":146,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Categorization; Text categorization; Sorting; Set (abstract data type); Support vector machine; Artificial intelligence; Vocabulary; Feature (linguistics); Natural language processing; Information retrieval; Process (computing); Feature vector","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":[0.00009643464,0.00005992852,0.00005580956,0.00006231396,0.00007105281,0.00009500469,0.0003143681,0.00003760693,0.0001124533],"category_scores_gemma":[0.00009176708,0.00004760844,0.00002700431,0.0001986557,0.00001572319,0.0003072124,0.00002669201,0.00002336691,0.00008012522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001448722,"about_ca_system_score_gemma":0.00003266957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002815788,"about_ca_topic_score_gemma":0.000002627773,"domain_scores_codex":[0.9995108,0.000009061888,0.0001071723,0.0001784536,0.0000745645,0.0001199395],"domain_scores_gemma":[0.9995708,0.00003705822,0.00003853439,0.0002851201,0.00004685183,0.00002157213],"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":[3.972883e-7,0.00001450326,0.0003895808,0.000002566749,0.000001888897,1.082012e-7,0.00003048733,0.000001531942,0.001172717,0.9752176,0.004960276,0.01820836],"study_design_scores_gemma":[0.0006186058,0.0001979388,0.003471085,0.00000196946,0.000005867747,0.000008139508,0.00008002784,0.01421932,0.2052138,0.3157833,0.4600383,0.0003616383],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006294516,0.00001264966,0.9766536,0.002131676,0.0002308965,0.0001541201,7.083727e-7,0.0005892997,0.01959759],"genre_scores_gemma":[0.9184598,0.00000444505,0.07218964,0.0001987578,0.00001122563,0.00005850771,0.000005572235,0.000004346626,0.009067714],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9178303,"threshold_uncertainty_score":0.1941416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01982714791796406,"score_gpt":0.2626373654355585,"score_spread":0.2428102175175944,"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."}}