{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005243199,0.0002597394,0.0002650801,0.0001381137,0.0009650426,0.0003113313,0.0008810933,0.0003953823,0.000004131219],"category_scores_gemma":[0.00004341754,0.0003176001,0.0001161619,0.0002422578,0.0001334683,0.0002077273,0.001122925,0.0004877143,0.00001374137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002464803,"about_ca_system_score_gemma":0.0001807523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005031553,"about_ca_topic_score_gemma":0.00001412359,"domain_scores_codex":[0.9982368,0.0002071181,0.0002221453,0.000867352,0.0001077345,0.0003588797],"domain_scores_gemma":[0.9983979,0.00004725527,0.0005920371,0.0006407411,0.0002032658,0.0001187984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008520097,0.000156773,0.01234051,0.0001982832,0.000119176,0.000111183,0.002050267,0.7467849,0.0005771923,0.2268048,0.0000229893,0.01074869],"study_design_scores_gemma":[0.0002854455,0.00001119841,0.01420638,0.00007224515,0.00004841576,0.000004282486,0.00004020872,0.9807218,0.00003021736,0.004185068,0.00007383685,0.0003208462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4665403,0.00004430622,0.5323858,0.00005356626,0.0005756383,0.0001897556,0.000009139829,0.000114844,0.00008662642],"genre_scores_gemma":[0.9975354,0.00004532496,0.001942609,0.00003887566,0.0001746155,6.11109e-7,0.00007641075,0.00001460814,0.0001715145],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5309951,"threshold_uncertainty_score":0.9999276,"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."}}