{"id":"W2068138600","doi":"10.1145/2492517.2492637","title":"Battling the internet water army","year":2013,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":184,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"The Internet; Internet privacy; Computer science; TRACE (psycholinguistics); World Wide Web; Sentiment analysis; Semantic analysis (machine learning); China; Internet users; Political science; Information retrieval; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001130066,0.00003542576,0.00002587214,0.00001547243,0.00004469591,0.0002804625,0.0003946344,0.00001536067,0.0003739726],"category_scores_gemma":[0.00000522328,0.00001532561,0.00001884973,0.00004256046,0.000009830688,0.0003077166,0.0001168191,0.00005673342,0.001974057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005982845,"about_ca_system_score_gemma":0.000002049544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004105683,"about_ca_topic_score_gemma":0.000008971552,"domain_scores_codex":[0.99966,0.00001776003,0.00005330562,0.00009787468,0.00006794505,0.0001030716],"domain_scores_gemma":[0.99972,0.00002664659,0.000007235536,0.0002071102,0.00001948709,0.00001953965],"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":[0.000004430007,0.00008493815,0.003921816,0.00001528792,0.00006757118,0.000006204999,0.01855783,0.0003099708,0.05458755,0.1501222,0.2421931,0.5301291],"study_design_scores_gemma":[0.0002326302,0.0001014732,0.00822462,0.00001185232,0.000004186641,0.00004132059,0.0001020511,0.443527,0.3799718,0.03945829,0.1280217,0.0003031528],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2357226,0.00001298182,0.7352465,0.00727835,0.0009845826,0.00008819631,1.930642e-8,0.0002199108,0.02044687],"genre_scores_gemma":[0.9925123,6.106268e-7,0.002359825,0.001020378,0.00007306878,0.00000836605,1.410387e-7,0.000001977091,0.004023326],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7567897,"threshold_uncertainty_score":0.998803,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01170349861037651,"score_gpt":0.1946039803168215,"score_spread":0.182900481706445,"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."}}