{"id":"W2994813639","doi":"10.5539/cis.v13n3p57","title":"Topic Subject Creation Using Unsupervised Learning for Topic Modeling","year":2020,"lang":"en","type":"preprint","venue":"Computer and Information Science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Latent Dirichlet allocation; Topic model; Non-negative matrix factorization; Subject (documents); Computer science; Artificial intelligence; Machine learning; Matrix decomposition; Data science; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004339429,0.000983068,0.001213148,0.003183,0.000943457,0.001837953,0.001596651,0.001098453,0.001492322],"category_scores_gemma":[0.01231785,0.0004322084,0.001709681,0.00307232,0.000867211,0.002395874,0.0014135,0.001855824,0.001630473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005823014,"about_ca_system_score_gemma":0.001123894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002016339,"about_ca_topic_score_gemma":0.002931882,"domain_scores_codex":[0.9972146,0.001369459,0.0001313575,0.0007446193,0.0003918105,0.0001481422],"domain_scores_gemma":[0.9895667,0.007851208,0.000541093,0.001088947,0.0007399925,0.000211961],"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":[0.0005142719,0.0007870633,0.008453275,0.000631542,0.00038913,0.0002664395,0.002205728,0.09478772,0.01876227,0.02633563,0.01106799,0.8357989],"study_design_scores_gemma":[0.00003313408,0.0001289438,0.001842289,0.0000309533,0.00006914844,0.0001669456,0.0001490248,0.9560905,0.006688599,0.02729836,0.00745292,0.0000492262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01188217,0.000437934,0.9856942,0.000155749,0.00007871869,0.0001137451,0.0002292673,0.000818758,0.0005895019],"genre_scores_gemma":[0.2226442,0.0008025294,0.7688345,0.0001737079,0.0006247808,0.0006712835,0.002741466,0.0003477978,0.003159649],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004339429,"threshold_uncertainty_score":0.02294934,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.050476913095002,"score_gpt":0.3225352121898026,"score_spread":0.2720582990948006,"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."}}