{"id":"W4239254818","doi":"10.29173/cais394","title":"Ditch the Smileys: Customizing a Stopword List for Email-based Data","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.002317019,0.0005285373,0.0008780725,0.0002100515,0.0005801891,0.01091395,0.01206072,0.0002662408,0.00008383414],"category_scores_gemma":[0.02754059,0.0003630418,0.0004024528,0.001135016,0.001256423,0.02130395,0.003472349,0.0005548972,0.00002051505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000751609,"about_ca_system_score_gemma":0.0008489012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003559232,"about_ca_topic_score_gemma":0.0001176888,"domain_scores_codex":[0.9961981,0.00009337311,0.0009956695,0.0009725399,0.0008057848,0.0009345579],"domain_scores_gemma":[0.9435481,0.001180228,0.001828132,0.001785311,0.05136821,0.000289961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003229263,0.001358243,0.0853022,0.003655465,0.001479567,0.000005467935,0.07852534,0.000175378,0.01505189,0.09798656,0.4804824,0.2356546],"study_design_scores_gemma":[0.001824321,0.0006145844,0.01539411,0.002491826,0.001048325,0.00004927294,0.007370375,0.3630185,0.01261753,0.008311681,0.5860681,0.001191394],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8502672,0.003301601,0.01521446,0.1182488,0.001729261,0.002311226,0.003767458,0.000175016,0.004984987],"genre_scores_gemma":[0.9860518,0.0001550228,0.009023577,0.0009474842,0.0004118794,0.0001164919,0.00004979861,0.000043311,0.003200649],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3628431,"threshold_uncertainty_score":0.9998822,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06965376117248033,"score_gpt":0.2781279929236916,"score_spread":0.2084742317512112,"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."}}