{"id":"W1978022428","doi":"10.1109/icdm.2014.120","title":"Mining Contentious Documents Using an Unsupervised Topic Model Based Approach","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Latent Dirichlet allocation; Topic model; Computer science; Viewpoints; Artificial intelligence; Probabilistic logic; Cluster analysis; Expression (computer science); Domain (mathematical analysis); Natural language processing; Information retrieval; Machine learning; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002756175,0.0001457571,0.0001979986,0.0001436213,0.0001188088,0.0001604049,0.0007965114,0.0000550707,0.00000888607],"category_scores_gemma":[0.00002075108,0.0001307413,0.00007582046,0.0002629912,0.0000278782,0.0009437298,0.0001392148,0.00006843734,0.000002915737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004636437,"about_ca_system_score_gemma":0.00002926391,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004226888,"about_ca_topic_score_gemma":0.00000737659,"domain_scores_codex":[0.9987274,0.00007944107,0.0002236088,0.0004566562,0.0002561655,0.000256678],"domain_scores_gemma":[0.9989296,0.00002703364,0.00007191657,0.0007841353,0.000087196,0.000100071],"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":[0.00001387036,0.001003091,0.006180502,0.00006175836,0.00009725667,0.000008140372,0.001113117,0.4838303,0.039751,0.2639069,0.0002310213,0.203803],"study_design_scores_gemma":[0.0002799297,0.00003350154,0.00004173962,0.000006043085,0.000009716824,0.00000143365,0.0000172703,0.9903551,0.003635549,0.005384369,0.00006311224,0.0001722535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05163695,0.00000676231,0.9416006,0.00004275056,0.00002415919,0.0001060143,1.535625e-7,0.0004642844,0.006118347],"genre_scores_gemma":[0.5007099,2.506379e-7,0.4986919,0.0003789147,0.00001067081,0.000006208974,0.000002195117,0.000006002144,0.0001939389],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5065248,"threshold_uncertainty_score":0.5331477,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04839903355945884,"score_gpt":0.30069312434877,"score_spread":0.2522940907893111,"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."}}