{"id":"W2162987981","doi":"","title":"A characterization of wordnet features in Boolean models for text classification","year":2006,"lang":"en","type":"article","venue":"Australasian Data Mining Conference","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"","keywords":"WordNet; Computer science; Artificial intelligence; Naive Bayes classifier; Natural language processing; Classifier (UML); Support vector machine; Weighting; Machine learning; Information retrieval","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":[0.0002154147,0.0001302377,0.0001715171,0.0002176839,0.000046295,0.0001668876,0.001754175,0.0001105316,0.000006645283],"category_scores_gemma":[0.00005827891,0.0001320119,0.00002103956,0.0003761001,0.0000806949,0.001581641,0.0002332567,0.00008989969,0.000003281437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002400158,"about_ca_system_score_gemma":0.00009273928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000462287,"about_ca_topic_score_gemma":0.0001002785,"domain_scores_codex":[0.9987105,0.00002694645,0.000379669,0.0005035747,0.0001575186,0.0002218585],"domain_scores_gemma":[0.9983733,0.000061697,0.0002726864,0.001184184,0.00008325969,0.00002488141],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00001969556,0.0001569599,0.005425821,0.00005629938,0.000009771071,0.000001589254,0.0005671293,0.00003654913,0.09066816,0.6431443,0.002416969,0.2574967],"study_design_scores_gemma":[0.00127153,0.0001757101,0.5208303,0.0002714995,0.00002226438,0.000009031654,0.0009065743,0.3923497,0.03126755,0.04726565,0.004946199,0.000683977],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1292161,0.00001832204,0.8656199,0.003059448,0.0001101397,0.0004250691,0.0001636401,0.0002318218,0.001155547],"genre_scores_gemma":[0.9435852,0.00001310358,0.05495611,0.00001858726,0.00002058318,0.00004521989,0.0008172205,0.000006908325,0.0005371289],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.814369,"threshold_uncertainty_score":0.5383291,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08786756615368328,"score_gpt":0.2996306411300966,"score_spread":0.2117630749764133,"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."}}