{"id":"W4388864379","doi":"10.17821/srels/2023/v60i5/170707","title":"Text Mining of Journal Article Titles: An LDA-Based Topic Modeling Approach","year":2023,"lang":"en","type":"article","venue":"Journal of Information and Knowledge","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Science North","funders":"","keywords":"Latent Dirichlet allocation; Topic model; Computer science; Data science; Field (mathematics); Scholarship; Information retrieval; Mathematics; Political 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":[0.00204451,0.00003816442,0.0001162497,0.0002948881,0.0001883649,0.00008495478,0.00009079902,0.0000328874,0.0000456962],"category_scores_gemma":[0.0002282263,0.0000300742,0.00006654377,0.0003811141,0.00003667986,0.0007390264,0.00001129411,0.00008734209,0.000008442275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002622387,"about_ca_system_score_gemma":0.0002595012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001142695,"about_ca_topic_score_gemma":0.00001691185,"domain_scores_codex":[0.9991342,0.0001206278,0.0004150752,0.00002374901,0.0002215742,0.00008476005],"domain_scores_gemma":[0.9991292,0.00009684868,0.0002569595,0.00002993295,0.0003930566,0.00009403944],"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":[0.00007487107,0.0001888922,0.004070148,0.0001146245,0.0001008798,0.000002962511,0.1533115,0.1016832,0.0002183198,0.01635521,0.002667652,0.7212117],"study_design_scores_gemma":[0.0004795205,0.00006398761,0.001968022,0.00004217376,0.00002649095,0.00001010703,0.02558454,0.9609464,0.00004208118,0.002056258,0.008715373,0.00006499862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8589087,0.0001244496,0.1198733,0.0002882874,0.0001871096,0.00003370395,8.475004e-7,0.00001098636,0.02057255],"genre_scores_gemma":[0.9884652,0.00004596234,0.01109678,0.00004298288,0.000178303,3.017612e-7,0.000001569552,0.000001705016,0.0001672259],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8592633,"threshold_uncertainty_score":0.1448769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06950786620653424,"score_gpt":0.3762300616837654,"score_spread":0.3067221954772311,"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."}}