{"id":"W2773782067","doi":"","title":"Chat Disentanglement: Identifying Semantic Reply Relationships with Random Forests and Recurrent Neural Networks","year":2017,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Thread (computing); Random forest; Recurrent neural network; Classifier (UML); Artificial intelligence; Machine learning; Artificial neural network; Natural language processing; Data mining; Programming language","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":[0.003155158,0.001503502,0.0009468862,0.002752788,0.0007243079,0.001159694,0.001670173,0.001323856,0.001641202],"category_scores_gemma":[0.008988333,0.0004414877,0.001084341,0.001421497,0.0004702559,0.00229264,0.001247327,0.0022187,0.001566684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005925386,"about_ca_system_score_gemma":0.0009297446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005649163,"about_ca_topic_score_gemma":0.01186592,"domain_scores_codex":[0.9987155,0.0004504313,0.00008588241,0.000409263,0.0001814825,0.0001575541],"domain_scores_gemma":[0.995201,0.002746862,0.0006579058,0.0005203387,0.0006354248,0.0002384384],"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":[0.0009850193,0.001041862,0.03801064,0.0002991072,0.0003162561,0.00049001,0.001373655,0.1247446,0.02222825,0.008482952,0.01237323,0.7896544],"study_design_scores_gemma":[0.00001332752,0.00004492322,0.001656668,0.00001342148,0.00002442117,0.00003675342,0.00008850621,0.9881421,0.002580139,0.006482776,0.0009024745,0.00001453598],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1688306,0.0007042571,0.8211468,0.0004794054,0.0001562678,0.0002240039,0.00114413,0.005163367,0.002151193],"genre_scores_gemma":[0.7638399,0.000176022,0.2265305,0.0001431346,0.000175316,0.0002484096,0.003817233,0.0002879011,0.004781576],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005649163,"threshold_uncertainty_score":0.01668626,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06351610469634573,"score_gpt":0.3261799200032158,"score_spread":0.2626638153068701,"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."}}