{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003249511,0.001123384,0.001028515,0.002066612,0.0004836948,0.002283506,0.001526976,0.001382187,0.001280149],"category_scores_gemma":[0.01462925,0.0006906347,0.001243743,0.00243753,0.0009936624,0.007302726,0.001969405,0.002930966,0.000791179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001018255,"about_ca_system_score_gemma":0.0007618552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002704159,"about_ca_topic_score_gemma":0.004554516,"domain_scores_codex":[0.9982303,0.0008850599,0.000135322,0.0003875955,0.0002780835,0.00008374254],"domain_scores_gemma":[0.9935684,0.004602468,0.0004352717,0.0007521223,0.0005070139,0.0001347105],"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":[0.0001885104,0.000182805,0.004373742,0.0003543922,0.0003045374,0.0001400979,0.0007409954,0.4615845,0.003720583,0.1375261,0.003955358,0.3869283],"study_design_scores_gemma":[0.000004976025,0.00001946011,0.0002328121,0.0000172997,0.00001765096,0.00003212897,0.00002715879,0.9382377,0.0004139181,0.05986486,0.001118899,0.00001317037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01063117,0.0008785038,0.9867377,0.0004188168,0.00005793687,0.00002591688,0.0001139097,0.0003442584,0.0007918978],"genre_scores_gemma":[0.5771784,0.002860717,0.4137826,0.0003769936,0.0005512823,0.0002746121,0.001191964,0.00027122,0.00351228],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003249511,"threshold_uncertainty_score":0.01718527,"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."}}