{"id":"W3197492799","doi":"10.1007/978-3-030-86331-9_23","title":"Sparse Document Analysis Using Beta-Liouville Naive Bayes with Vocabulary Knowledge","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; BETA (programming language); Bayes' theorem; Artificial intelligence; Naive Bayes classifier; Vocabulary; Natural language processing; Machine learning; Bayesian probability; Programming language; Philosophy; Linguistics; Support vector machine","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":[0.004192374,0.001187244,0.002759842,0.004696221,0.001583796,0.003546241,0.002511479,0.002158121,0.004550764],"category_scores_gemma":[0.01470317,0.001059356,0.002408501,0.004210253,0.001022413,0.004663728,0.001869747,0.002931861,0.003477809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001111311,"about_ca_system_score_gemma":0.002062989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007665755,"about_ca_topic_score_gemma":0.01020468,"domain_scores_codex":[0.9957832,0.001608598,0.0004376004,0.0007578874,0.001163009,0.0002498173],"domain_scores_gemma":[0.9913431,0.006081219,0.0002601412,0.0007851669,0.00138237,0.0001480402],"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":[0.0003778282,0.0002994145,0.002002542,0.0004151265,0.0003188792,0.0002030764,0.0002162156,0.07040436,0.006690847,0.02069374,0.01247087,0.8859071],"study_design_scores_gemma":[0.00003442281,0.00005076133,0.000338792,0.00004449684,0.00009746849,0.000146605,0.00004623229,0.953284,0.001992342,0.04112548,0.002809176,0.00003031719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003709006,0.000943533,0.9932582,0.0001485927,0.0000891207,0.00006927039,0.0002000395,0.0009409293,0.0006414213],"genre_scores_gemma":[0.1378013,0.001500354,0.8490766,0.0003460281,0.0007190761,0.0003662984,0.003163549,0.0003691017,0.006657627],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007665755,"threshold_uncertainty_score":0.02217162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02460182828816797,"score_gpt":0.260545632630907,"score_spread":0.235943804342739,"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."}}