{"id":"W2000918452","doi":"10.1145/1281192.1281260","title":"A concept-based model for enhancing text categorization","year":2007,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Natural language processing; Categorization; Sentence; Artificial intelligence; Phrase; Term (time); Weighting; Graph; Information retrieval; Theoretical computer science","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":[0.0002070395,0.00006303743,0.00005970197,0.00009536494,0.0000832271,0.0000735563,0.0003719279,0.00005345253,0.000007813404],"category_scores_gemma":[0.00005328581,0.00005477833,0.00002995145,0.0002182904,0.00002530069,0.0002816493,0.00003669229,0.00003166722,0.00001370216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000362874,"about_ca_system_score_gemma":0.00005388312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000425365,"about_ca_topic_score_gemma":0.00005880543,"domain_scores_codex":[0.9993671,0.000003286548,0.0001583843,0.0001970765,0.00010167,0.0001725454],"domain_scores_gemma":[0.9994721,0.00008748129,0.00005703214,0.0002800289,0.00007532422,0.00002807202],"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":[0.000002687566,0.0000221483,0.00003808089,0.000004072253,0.000001770857,1.662817e-7,0.0001793996,0.002350407,0.009137586,0.9396791,0.0008059966,0.0477786],"study_design_scores_gemma":[0.0001828135,0.0000218578,0.00005017675,0.000001644141,0.000001046072,1.620168e-7,0.00005096713,0.7843188,0.1988266,0.01566663,0.0008055213,0.00007376039],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005468536,0.00001366491,0.9955518,0.001387699,0.00007908075,0.0001765791,5.409963e-7,0.0007395489,0.001504216],"genre_scores_gemma":[0.8124476,5.452409e-7,0.1857898,0.0003336122,0.00001038607,0.00001896411,0.00000393899,0.000003338093,0.001391774],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9240125,"threshold_uncertainty_score":0.2233796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02597749126124376,"score_gpt":0.281605414501903,"score_spread":0.2556279232406592,"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."}}