{"id":"W4244795915","doi":"10.32920/ryerson.14654349","title":"Identifying User Interests In An Online Discussion Forum With Deep Learning","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; Ontario Tech University","funders":"","keywords":"Latent Dirichlet allocation; Computer science; Topic model; Artificial neural network; Metric (unit); Set (abstract data type); Sample (material); Artificial intelligence; Probabilistic logic; Machine learning; Social media; Recommender system; Test set; Data set; Data mining; World Wide Web; Engineering","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":[0.003897632,0.0006347803,0.0004342271,0.001758392,0.0006197288,0.001306939,0.0007871598,0.0009584333,0.001316289],"category_scores_gemma":[0.00879554,0.0004353188,0.0005834633,0.0009860641,0.0004062117,0.002219592,0.001420602,0.001600521,0.0006136681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001307572,"about_ca_system_score_gemma":0.0007580225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00680641,"about_ca_topic_score_gemma":0.01120411,"domain_scores_codex":[0.9987405,0.0005914906,0.00004678252,0.0002944643,0.0001682009,0.0001585401],"domain_scores_gemma":[0.9952627,0.003257358,0.0003292814,0.0003060968,0.0005936195,0.0002510077],"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":[0.002570387,0.002870197,0.1529683,0.0005094622,0.0003772162,0.0005340375,0.00891769,0.267384,0.03804667,0.01428694,0.007648958,0.5038862],"study_design_scores_gemma":[0.00001225359,0.00008140787,0.006075306,0.00001115552,0.00001288152,0.00002222416,0.0001931779,0.9864362,0.002838099,0.003587734,0.0007151107,0.00001450579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8202277,0.0002875245,0.1726101,0.0004896334,0.00004781389,0.0002175939,0.0008688229,0.001290033,0.003960858],"genre_scores_gemma":[0.9647848,0.00004251812,0.03262009,0.00003559773,0.00001284998,0.00008693241,0.0005020997,0.00002202826,0.001892984],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00680641,"threshold_uncertainty_score":0.0206129,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05758956287715514,"score_gpt":0.3124403340316915,"score_spread":0.2548507711545364,"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."}}