{"id":"W2340990333","doi":"10.1177/0165551515625030","title":"The impact of indexing approaches on Arabic text classification","year":2016,"lang":"en","type":"article","venue":"Journal of Information Science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Classifier (UML); Search engine indexing; Arabic; Artificial intelligence; Naive Bayes classifier; Natural language processing; Pattern recognition (psychology); Word (group theory); Mathematics; Support vector machine","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":[0.001925785,0.0000642427,0.00008728581,0.00047141,0.0002182553,0.0002808968,0.001647536,0.00003108321,0.000002960765],"category_scores_gemma":[0.0009535845,0.00002670527,0.00007534585,0.0009720784,0.0003892191,0.007358836,0.0000861912,0.00008971629,0.00002589624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001706905,"about_ca_system_score_gemma":0.0003520497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001058237,"about_ca_topic_score_gemma":9.833091e-8,"domain_scores_codex":[0.9985344,0.00002216669,0.0005558532,0.00006602269,0.0006744868,0.000147108],"domain_scores_gemma":[0.9976785,0.0002250174,0.001181632,0.0003840883,0.0004817612,0.00004904726],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00001484388,0.00001988695,0.001503164,0.000001954023,0.000005814164,7.022848e-8,0.0005077799,0.0001607187,0.007371659,0.3357193,0.0004556811,0.6542391],"study_design_scores_gemma":[0.001428404,0.00144186,0.7550424,0.0002279804,0.000006886482,0.00009764985,0.002360692,0.05217132,0.1330754,0.04635817,0.007416472,0.0003727837],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2316907,0.00002968422,0.7531817,0.006925679,0.0002985455,0.0001329954,0.000001117662,0.00005438854,0.007685232],"genre_scores_gemma":[0.9970692,0.0000518655,0.002817614,0.00001998854,0.00001152843,0.000002011898,5.274321e-8,9.050483e-7,0.00002679051],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7653786,"threshold_uncertainty_score":0.5334978,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06173573844272501,"score_gpt":0.3028807703285067,"score_spread":0.2411450318857817,"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."}}