{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01136179,0.001040017,0.0008551364,0.005670841,0.001366238,0.003075583,0.001708332,0.001296632,0.00526248],"category_scores_gemma":[0.06303105,0.0006311751,0.0009759124,0.004275289,0.001421555,0.004409399,0.002562413,0.001748183,0.004102644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009074801,"about_ca_system_score_gemma":0.002449743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001926411,"about_ca_topic_score_gemma":0.004313068,"domain_scores_codex":[0.9909236,0.004502344,0.001369135,0.001030336,0.001971907,0.0002027484],"domain_scores_gemma":[0.9362501,0.04249659,0.004136804,0.006344778,0.01005393,0.0007178399],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000893211,0.0003825221,0.0173913,0.004528806,0.0001607392,0.0008017121,0.03352166,0.001900837,0.06769369,0.01502065,0.02143162,0.8362734],"study_design_scores_gemma":[0.0003834354,0.002400066,0.05906183,0.004150596,0.0006070595,0.003895968,0.0457266,0.1146553,0.1900776,0.06159766,0.516355,0.001088906],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0751917,0.0004451938,0.8964507,0.001122646,0.000408958,0.003586233,0.00356985,0.0137551,0.005469688],"genre_scores_gemma":[0.09436355,0.0002199539,0.8943262,0.0003786264,0.00005396092,0.001857241,0.003317328,0.001412212,0.004070926],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01136179,"threshold_uncertainty_score":0.06008762,"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."}}