{"id":"W2510939506","doi":"10.18653/v1/w16-0417","title":"Semi-supervised and unsupervised categorization of posts in Web discussion forums using part-of-speech information and minimal features","year":2016,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Categorization; Artificial intelligence; Cluster analysis; Hidden Markov model; Identification (biology); Probabilistic logic; Topic model; Natural language processing; Machine learning; Unsupervised learning; Information retrieval","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003552138,0.001203882,0.001048418,0.00485118,0.000838189,0.001185798,0.00153676,0.001050797,0.001089776],"category_scores_gemma":[0.008339812,0.0003995333,0.001292624,0.001706151,0.000788575,0.002355098,0.0009721799,0.0009437289,0.001979301],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006561615,"about_ca_system_score_gemma":0.001393224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001959364,"about_ca_topic_score_gemma":0.005219777,"domain_scores_codex":[0.9963233,0.001602864,0.0002357803,0.001107184,0.0005383478,0.0001924469],"domain_scores_gemma":[0.9913788,0.004748445,0.001105038,0.001005954,0.001471847,0.0002900079],"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":[0.001173445,0.001620093,0.04042068,0.00119683,0.0005475759,0.0002457558,0.00228656,0.03879073,0.04634752,0.004516859,0.01232058,0.8505334],"study_design_scores_gemma":[0.00006891559,0.0003781526,0.02871859,0.000103763,0.0001425611,0.0003625763,0.0008876164,0.9303477,0.02394957,0.009867778,0.005045996,0.0001266491],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2713593,0.0008771704,0.7160844,0.0002606212,0.0001438886,0.0007233865,0.001762429,0.004151946,0.004636838],"genre_scores_gemma":[0.7596779,0.0002754341,0.2278784,0.00009550573,0.0001926006,0.0005858872,0.006375972,0.0002445791,0.004673709],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00485118,"threshold_uncertainty_score":0.01878572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0154227995785618,"score_gpt":0.234658583576162,"score_spread":0.2192357839976002,"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."}}