{"id":"W1970043789","doi":"10.1145/1645953.1646076","title":"Detecting topic evolution in scientific literature","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":165,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"National Science Foundation","keywords":"Latent Dirichlet allocation; Computer science; Topic model; Data science; Citation; Inheritance (genetic algorithm); Scientific literature; Information retrieval; World Wide Web","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":[0.0002368335,0.00006376281,0.00007547873,0.0003010411,0.00008206994,0.0002677713,0.0004112652,0.00004021115,0.000003860107],"category_scores_gemma":[0.00004548704,0.00005574146,0.00003481483,0.001557235,0.0000135609,0.0008026955,0.00005519394,0.0001133071,0.000009899591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008328947,"about_ca_system_score_gemma":0.00001579977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004640381,"about_ca_topic_score_gemma":0.00003847483,"domain_scores_codex":[0.9992388,0.00002404926,0.0001308867,0.0002953446,0.0001419681,0.0001688751],"domain_scores_gemma":[0.9994776,0.00001512343,0.00003226987,0.0003941212,0.00005432241,0.00002652169],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001660967,0.00007905807,0.003108842,0.000004995446,0.000002612986,0.00003044942,0.0009665766,0.0001716749,0.05595215,0.4716208,0.0002304384,0.4678307],"study_design_scores_gemma":[0.0002747195,0.0001257587,0.07230069,0.000120887,0.000003420995,0.00002419438,0.00003660046,0.1264195,0.07166678,0.7265724,0.002002954,0.0004520738],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04784755,0.000207644,0.9479027,0.0004176419,0.00006832802,0.00005906055,4.775541e-8,0.0003461228,0.00315088],"genre_scores_gemma":[0.8388192,0.00000131365,0.1603789,0.00009707922,0.00001551372,0.000001889024,4.390623e-7,0.000001148629,0.0006844748],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7909717,"threshold_uncertainty_score":0.2582124,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006675345525235707,"score_gpt":0.262146813315761,"score_spread":0.2554714677905253,"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."}}