{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002537238,0.001121492,0.001084888,0.007083457,0.0009544989,0.002453885,0.001846538,0.001388847,0.0008496435],"category_scores_gemma":[0.007229303,0.000604461,0.001891616,0.004256872,0.0006910187,0.002422668,0.00135499,0.001314094,0.0007420438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007375157,"about_ca_system_score_gemma":0.001259195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001886453,"about_ca_topic_score_gemma":0.003834234,"domain_scores_codex":[0.9973102,0.0008016726,0.0002417228,0.0007223532,0.0007455234,0.0001786085],"domain_scores_gemma":[0.9953684,0.00289461,0.0004593082,0.0003852702,0.00077838,0.0001141173],"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":[0.0008672681,0.0006793413,0.02719924,0.001225564,0.001082151,0.001690546,0.005561105,0.066879,0.06132847,0.03114689,0.01206636,0.7902741],"study_design_scores_gemma":[0.00008915158,0.0001811968,0.009951571,0.00009476942,0.0003402541,0.0008406285,0.001453248,0.9222146,0.01447749,0.03882478,0.01144648,0.00008586865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05441443,0.0008837329,0.9410255,0.0002836274,0.00006435302,0.0002346783,0.0005822909,0.0009263844,0.001585029],"genre_scores_gemma":[0.4963487,0.0007563964,0.494911,0.0001607613,0.0003719538,0.0006176914,0.00386853,0.000227268,0.002737777],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007083457,"threshold_uncertainty_score":0.01341832,"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."}}