{"id":"W2184821933","doi":"10.1007/s10115-015-0888-6","title":"Mining contentious documents","year":2015,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Information retrieval; Natural language processing; Data science","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":[0.001910277,0.001139761,0.001358361,0.01741617,0.002125046,0.004419041,0.001756486,0.001692286,0.003062992],"category_scores_gemma":[0.01547543,0.0008602882,0.001642018,0.01090234,0.0009528828,0.006495085,0.001591307,0.00155104,0.002451992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001045695,"about_ca_system_score_gemma":0.001889289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002241594,"about_ca_topic_score_gemma":0.003899693,"domain_scores_codex":[0.996663,0.0006776195,0.0003434611,0.0008393435,0.001185196,0.0002913416],"domain_scores_gemma":[0.9893011,0.005764148,0.000969129,0.001528882,0.002031063,0.0004055273],"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":[0.001469191,0.001016339,0.04341316,0.001971798,0.001068291,0.002077898,0.002465201,0.01391486,0.04632259,0.02810717,0.03455904,0.8236145],"study_design_scores_gemma":[0.000298163,0.001026938,0.06112778,0.0008124799,0.002547618,0.006309886,0.004351198,0.4878687,0.1136696,0.1743171,0.147402,0.0002685072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.450472,0.01718466,0.4925087,0.003156893,0.000641648,0.0008890263,0.01279466,0.004954062,0.01739832],"genre_scores_gemma":[0.7850077,0.005147987,0.1745535,0.0003456159,0.001287107,0.0003744297,0.018356,0.0005329968,0.01439462],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01741617,"threshold_uncertainty_score":0.01024675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0373270025936249,"score_gpt":0.2637436142519596,"score_spread":0.2264166116583347,"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."}}