{"id":"W123190706","doi":"","title":"Topic Classification of Blog Posts Using Distant Supervision","year":2012,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Blogosphere; Computer science; Classifier (UML); Vocabulary; Binary classification; Artificial intelligence; Class (philosophy); Information retrieval; Sample (material); Natural language processing; Data science; World Wide Web; Support vector machine; The Internet","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":[],"consensus_categories":[],"category_scores_codex":[0.0001452846,0.00006081935,0.00007586728,0.00008566248,0.00004692284,0.00003113683,0.0004132775,0.00005199353,0.00003604541],"category_scores_gemma":[0.00002279546,0.00004759428,0.00003028534,0.0002379992,0.00003813648,0.0005876655,0.0001348526,0.00004072651,0.00002056247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000308754,"about_ca_system_score_gemma":0.0000154412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001546881,"about_ca_topic_score_gemma":0.000001089505,"domain_scores_codex":[0.999363,0.00001910725,0.0001826369,0.000131502,0.0001512414,0.0001524791],"domain_scores_gemma":[0.9993327,0.00003057577,0.00007622258,0.0004775751,0.00004822045,0.00003473513],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.000001003389,0.00006858008,0.02562535,0.000006758712,0.000003021025,8.646538e-8,0.0001707412,6.797654e-7,0.103094,0.8364867,0.0001095793,0.03443354],"study_design_scores_gemma":[0.0004947448,0.0001247151,0.5008795,0.00003813673,0.00001705958,0.00001301848,0.001215436,0.05846018,0.3989329,0.02915308,0.01019256,0.0004786101],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5691913,0.0001691481,0.4260618,0.0009181062,0.0002399469,0.00008093791,4.532967e-7,0.0002425691,0.003095706],"genre_scores_gemma":[0.9639726,0.00001212426,0.03580074,0.00003064035,0.00001570162,0.000002727528,0.000001437951,0.000002468575,0.0001615979],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8073336,"threshold_uncertainty_score":0.1940838,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06051903039669124,"score_gpt":0.3021238606092946,"score_spread":0.2416048302126033,"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."}}