{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004855881,0.001371583,0.001724634,0.02311014,0.001530365,0.003317236,0.001526659,0.0012425,0.001918513],"category_scores_gemma":[0.01038285,0.000571298,0.003027136,0.01579671,0.0006249035,0.002578951,0.001428902,0.001357851,0.002753712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001061703,"about_ca_system_score_gemma":0.002114645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005662297,"about_ca_topic_score_gemma":0.008019092,"domain_scores_codex":[0.9957945,0.001459096,0.0005737148,0.001042176,0.0008916284,0.0002389087],"domain_scores_gemma":[0.9935407,0.003884208,0.0007352151,0.0003938257,0.001277293,0.0001687808],"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":[0.0005882485,0.001081999,0.0408579,0.001899545,0.001381336,0.0005865928,0.003131898,0.02496118,0.01307088,0.007994124,0.03732221,0.8671241],"study_design_scores_gemma":[0.000179336,0.0005602339,0.0625146,0.0004677319,0.0012851,0.001403964,0.002800772,0.8145393,0.01105886,0.03305883,0.07175812,0.0003732649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09615222,0.007810235,0.8648672,0.00242473,0.0005566166,0.002114669,0.01463436,0.004849968,0.006590049],"genre_scores_gemma":[0.4567202,0.004082814,0.5062643,0.0003123754,0.001369754,0.002828843,0.0196206,0.0004570311,0.008344125],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02311014,"threshold_uncertainty_score":0.02568066,"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."}}