{"id":"W4403134937","doi":"10.1080/08839514.2024.2403904","title":"Integration of Neural Embeddings and Probabilistic Models in Topic Modeling","year":2024,"lang":"en","type":"article","venue":"Applied Artificial Intelligence","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Probabilistic logic; Artificial neural network; Statistical model; Artificial intelligence; Machine learning; Data mining; Data science; Theoretical computer science","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":[0.0002478132,0.0001167401,0.0001694619,0.000225292,0.00003127893,0.0001164873,0.0003179151,0.00005163978,0.00000297732],"category_scores_gemma":[0.00002969354,0.000107679,0.00003500037,0.0006123945,0.00006106499,0.0004628247,0.0001296821,0.0001611644,0.000004246773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003883992,"about_ca_system_score_gemma":0.00002299551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005883065,"about_ca_topic_score_gemma":0.00007662445,"domain_scores_codex":[0.9988509,0.00001576907,0.0004167596,0.0004000042,0.0001544877,0.0001621258],"domain_scores_gemma":[0.9995428,0.00009021293,0.00004121133,0.0002475104,0.00004640629,0.0000318983],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002162423,0.00001234906,8.252663e-7,0.00001606614,0.000002029695,0.000001788075,0.001062062,0.09900569,0.01175388,0.6604986,6.604199e-7,0.2276439],"study_design_scores_gemma":[0.000002347001,0.000009549275,7.80935e-7,0.00002439279,0.000002401017,8.644284e-7,0.00005113675,0.5289627,0.01830921,0.45258,0.000001997342,0.00005469645],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09330433,0.0001534017,0.9055214,0.0001195629,0.00004852145,0.0001756157,4.311204e-7,0.0001622103,0.0005145135],"genre_scores_gemma":[0.9405581,0.00002650842,0.05931877,0.000025113,0.00001954145,0.00003679,0.000001048182,0.000006939371,0.000007178092],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8472538,"threshold_uncertainty_score":0.439102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06095076820110108,"score_gpt":0.318660209183276,"score_spread":0.257709440982175,"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."}}