{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004761584,0.0001983031,0.0001829313,0.0001295117,0.0008634407,0.001760102,0.00068506,0.00005331276,0.00001652081],"category_scores_gemma":[0.0004774898,0.0001523613,0.00004901228,0.0000807584,0.00009931863,0.001359139,0.0002829728,0.0005359756,0.000005553384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000624452,"about_ca_system_score_gemma":0.00004417979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003073478,"about_ca_topic_score_gemma":0.0001091905,"domain_scores_codex":[0.9984443,0.00008767071,0.0002896837,0.0004708306,0.0004439235,0.0002636003],"domain_scores_gemma":[0.9986967,0.00007818523,0.0004329815,0.0003594735,0.0003307344,0.0001019514],"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":[0.0005283774,0.0001295612,0.07985589,0.0001836141,0.0001427683,0.0004323967,0.005701865,0.0005740831,0.0005999653,0.07409701,0.0001143733,0.8376401],"study_design_scores_gemma":[0.001048524,0.00003836445,0.06042236,0.0006673621,0.00001405092,0.00006222261,0.0002591027,0.9357601,0.0004636142,0.0009616104,0.00003605854,0.0002666046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2682411,0.003101033,0.7092617,0.01348873,0.002784909,0.0005871138,0.00001102582,0.0003443387,0.002180026],"genre_scores_gemma":[0.9964262,0.00002452403,0.002806823,0.000272959,0.0002055276,0.00001753665,0.00003254463,0.00001079683,0.0002031295],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.935186,"threshold_uncertainty_score":0.9992762,"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."}}