{"id":"W4392231600","doi":"10.1007/s10044-024-01213-y","title":"Big topic modeling based on a two-level hierarchical latent Beta-Liouville allocation for large-scale data and parameter streaming","year":2024,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Scale (ratio); BETA (programming language); Big data; Artificial intelligence; Data mining; Physics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00614347,0.001058317,0.002758014,0.001741289,0.001530589,0.002430227,0.004156327,0.002355657,0.003584002],"category_scores_gemma":[0.01723167,0.001303645,0.002531951,0.002747174,0.001737276,0.004847833,0.003227199,0.003967502,0.001378697],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001571851,"about_ca_system_score_gemma":0.00222287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00774925,"about_ca_topic_score_gemma":0.01284001,"domain_scores_codex":[0.9972835,0.001402035,0.0001465603,0.000557707,0.0003468309,0.0002634482],"domain_scores_gemma":[0.9891951,0.007915907,0.0004121685,0.001180571,0.0008287808,0.000467512],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004640775,0.0003171176,0.003611532,0.0003183425,0.0003361616,0.0002848635,0.000830774,0.6082985,0.005709331,0.2221396,0.008772423,0.1489172],"study_design_scores_gemma":[0.000006939877,0.000007743418,0.0000797248,0.000003297915,0.000008218305,0.000009775518,0.000009688988,0.9810464,0.0001322177,0.01843419,0.0002536328,0.000008209632],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005623547,0.0001970658,0.993414,0.0001422538,0.00003445959,0.0000271833,0.00006658165,0.0002888815,0.0002061051],"genre_scores_gemma":[0.3747515,0.001016945,0.6122284,0.0005342499,0.0006122773,0.0008771525,0.001934594,0.0006639002,0.007380982],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00774925,"threshold_uncertainty_score":0.03249013,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07047955069751044,"score_gpt":0.3082657168572723,"score_spread":0.2377861661597618,"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."}}