{"id":"W2109753595","doi":"10.1109/lsp.2010.2048940","title":"Self-Organizing Maps for Topic Trend Discovery","year":2010,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Mitacs","keywords":"Latent Dirichlet allocation; Computer science; Topic model; Visualization; Dimensionality reduction; Data mining; Information retrieval; Set (abstract data type); Data visualization; Process (computing); Latent semantic analysis; Curse of dimensionality; Artificial intelligence; Machine learning","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000211468,0.0001968985,0.0002039286,0.0001666672,0.0002604843,0.0005315181,0.0008711763,0.00007259452,0.000002930335],"category_scores_gemma":[0.00001591536,0.0001825856,0.0001084179,0.0004078719,0.00006013949,0.001759152,0.00007430538,0.0002756022,0.000005600524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004390914,"about_ca_system_score_gemma":0.00005467973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003235865,"about_ca_topic_score_gemma":0.000009506071,"domain_scores_codex":[0.9986048,0.00001940664,0.0002501283,0.0004999079,0.0002480552,0.000377697],"domain_scores_gemma":[0.9992598,0.00008865373,0.0001610828,0.0003653646,0.00005454966,0.00007055463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000003804154,0.00004552412,0.000161375,0.00007535877,0.00002229769,0.00001115402,0.0004644052,0.00004925289,0.9151062,0.001591614,0.001807226,0.08066173],"study_design_scores_gemma":[0.0006428643,0.00009838337,0.0001669279,0.00008837896,0.00007847898,0.00004484893,0.00002955137,0.04394938,0.9122382,0.01726282,0.02439787,0.001002314],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05314801,0.00003709009,0.9432662,0.002344093,0.0002255656,0.0001433171,0.000002074431,0.0006793345,0.0001543487],"genre_scores_gemma":[0.6660002,0.00000102881,0.3318475,0.001725972,0.0002903719,0.00002886358,0.000003062072,0.00002001324,0.00008298265],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6128522,"threshold_uncertainty_score":0.7445623,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01012035866637828,"score_gpt":0.2520302530256199,"score_spread":0.2419098943592417,"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."}}