{"id":"W2132052677","doi":"10.14569/ijacsa.2015.060121","title":"A Survey of Topic Modeling in Text Mining","year":2015,"lang":"en","type":"article","venue":"International Journal of Advanced Computer Science and Applications","topic":"Topic Modeling","field":"Computer Science","cited_by":368,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Latent Dirichlet allocation; Topic model; Computer science; Probabilistic latent semantic analysis; Natural language processing; Artificial intelligence; Latent semantic analysis; Field (mathematics); Probabilistic logic; Information retrieval","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":[],"consensus_categories":[],"category_scores_codex":[0.001101844,0.00005664514,0.0001193816,0.0003232212,0.00003015893,0.00008745848,0.001292682,0.00001594633,3.263068e-7],"category_scores_gemma":[0.00009499086,0.0000519591,0.00001794732,0.000521121,0.00007077682,0.0008849879,0.0002662585,0.00007877204,5.662682e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007608223,"about_ca_system_score_gemma":0.0003490605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003699618,"about_ca_topic_score_gemma":0.00001336458,"domain_scores_codex":[0.9987232,0.00002120508,0.0003920246,0.0001799332,0.0005748692,0.0001087445],"domain_scores_gemma":[0.9979047,0.00007228962,0.0002028757,0.0001787693,0.001549522,0.00009186235],"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":[0.000007515986,0.00006513439,0.003986649,0.000002586235,0.000007456737,0.000004941228,0.0009720907,0.2302879,0.0005925843,0.01371821,0.00001129777,0.7503436],"study_design_scores_gemma":[0.0003720721,0.00004209414,0.004615111,0.00003659407,8.451876e-7,0.00004163398,0.00005191677,0.9896502,0.000208815,0.004713719,0.0002066746,0.00006029674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2126212,0.0001156191,0.786495,0.0003925282,0.0002330919,0.00004675342,6.395013e-7,0.000005181421,0.00008999136],"genre_scores_gemma":[0.803445,0.00001764462,0.1963752,0.00009017181,0.00006426326,0.000003108125,2.233032e-7,0.000001534152,0.000002846726],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7593623,"threshold_uncertainty_score":0.2402146,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0669373198898449,"score_gpt":0.3294273301311625,"score_spread":0.2624900102413176,"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."}}