{"id":"W2898962309","doi":"10.5539/cis.v11n4p77","title":"Topic Modelling in Bangla Language: An LDA Approach to Optimize Topics and News Classification","year":2018,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Latent Dirichlet allocation; Topic model; Bengali; Natural language processing; Bigram; Artificial intelligence; Language model; Similarity (geometry); Information retrieval; Categorization; Popularity; Document clustering; Cluster analysis; Trigram","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008969098,0.0000428188,0.00006469652,0.0002097726,0.0003146495,0.00031571,0.0001499891,0.00002340312,0.000004810657],"category_scores_gemma":[0.00003693816,0.00003848092,0.000008331588,0.0006437815,0.0002085373,0.002507659,0.00005659556,0.0000377941,0.000004617929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002702637,"about_ca_system_score_gemma":0.00006413608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003149933,"about_ca_topic_score_gemma":0.00004662303,"domain_scores_codex":[0.9993301,0.0000475737,0.0001574918,0.0001250459,0.0002214983,0.000118273],"domain_scores_gemma":[0.9996101,0.00002865861,0.00003993511,0.00007958402,0.0001411655,0.0001005088],"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":[0.000004019646,0.00001660369,0.001743472,0.000006005184,0.000001183349,7.47502e-8,0.07676471,0.00910745,0.00001346567,0.07635713,0.0000399691,0.8359459],"study_design_scores_gemma":[0.00008586676,0.00002182179,0.02235526,0.000004092612,0.000001364867,6.110507e-7,0.002552283,0.9687555,0.000009937447,0.0006539819,0.005494312,0.00006491607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2804289,0.000009190735,0.7038561,0.0004052387,0.00008787241,0.000086188,3.455375e-7,0.00001626829,0.01510985],"genre_scores_gemma":[0.7870407,0.00001450789,0.2120937,0.000621759,0.0001747881,0.000003382144,0.000002992831,7.697647e-7,0.00004743965],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9596481,"threshold_uncertainty_score":0.3044398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06869610714418223,"score_gpt":0.3682764751611717,"score_spread":0.2995803680169895,"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."}}