{"id":"W2952204729","doi":"10.48550/arxiv.1702.06467","title":"Efficient Social Network Multilingual Classification using Character, POS n-grams and Dynamic Normalization","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Normalization (sociology); Hyperlink; Computer science; Natural language processing; Artificial intelligence; Support vector machine; Social media; Information retrieval; World Wide Web; Web page","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009563818,0.001214487,0.0009582987,0.005018644,0.0009724128,0.001560447,0.0007002502,0.0006712551,0.003361732],"category_scores_gemma":[0.004447668,0.0002516254,0.000667083,0.004080587,0.000410152,0.00225275,0.001200888,0.0009682462,0.006616672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007738903,"about_ca_system_score_gemma":0.0008291127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002816581,"about_ca_topic_score_gemma":0.004588026,"domain_scores_codex":[0.9986266,0.0003125034,0.0001109174,0.0004041075,0.0003947503,0.0001511369],"domain_scores_gemma":[0.9978442,0.0005964895,0.0003209786,0.0004995871,0.0006306069,0.0001082115],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000398754,0.0002770573,0.009774628,0.0001698091,0.0001103237,0.0002691225,0.0002826433,0.01007611,0.03392546,0.004030416,0.01629471,0.924391],"study_design_scores_gemma":[0.00003223618,0.000150372,0.02283181,0.00007236579,0.00009838086,0.0007722412,0.0007761073,0.85131,0.0572177,0.03253547,0.03408973,0.0001136034],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.162705,0.001543617,0.7925394,0.0009328395,0.0006446196,0.0004643017,0.004706009,0.02347876,0.01298527],"genre_scores_gemma":[0.5669011,0.0006232882,0.4027775,0.0002113756,0.0004606567,0.0004968287,0.01278932,0.0009400607,0.01479991],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005018644,"threshold_uncertainty_score":0.01124609,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1432087976010132,"score_gpt":0.2575021246758563,"score_spread":0.1142933270748431,"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."}}