{"id":"W1541367332","doi":"10.1007/978-3-642-21043-3_15","title":"Exploiting Conversational Features to Detect High-Quality Blog Comments","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"CRFS; Computer science; Conditional random field; Quality (philosophy); Natural language processing; Artificial intelligence; Moderation; Social media; Binary number; Information retrieval; Machine learning; World Wide Web; Mathematics","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":[0.001303809,0.0005286444,0.0005479587,0.0006930816,0.0003089366,0.000433516,0.003876222,0.0003079862,0.00004848936],"category_scores_gemma":[0.0001530255,0.0005133112,0.000125798,0.0004011396,0.0003040755,0.0005244876,0.002215284,0.0008157471,0.00008281982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003799184,"about_ca_system_score_gemma":0.0003790463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002006997,"about_ca_topic_score_gemma":0.0001156781,"domain_scores_codex":[0.9955261,0.0000694648,0.0006526578,0.001793298,0.001227475,0.0007309826],"domain_scores_gemma":[0.9969651,0.0005530772,0.0003232749,0.001598516,0.0002840959,0.0002759048],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001285825,0.00002498879,0.0001730844,0.00004980805,0.00002651695,0.00006744487,0.002266619,0.01522165,0.0003861475,0.1530309,0.00006488999,0.8286751],"study_design_scores_gemma":[0.0006839145,0.0002586299,0.002205941,0.0006237787,0.00001466682,0.0000799333,7.833497e-7,0.05738965,0.007299718,0.928382,0.001302352,0.001758596],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000728427,0.0001086121,0.9921096,0.001227091,0.002257208,0.000405735,0.000007640755,0.0002091067,0.002946571],"genre_scores_gemma":[0.3513856,0.000007444158,0.6423882,0.005433782,0.0004704134,0.00001427182,0.000004814787,0.00002816107,0.000267374],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8269165,"threshold_uncertainty_score":0.9997318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04797135374995147,"score_gpt":0.2776049032620959,"score_spread":0.2296335495121444,"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."}}