{"id":"W2973161955","doi":"10.2218/ijdc.v14i1.586","title":"Identifying Topical Coverages of Curricula using Topic Modeling and Visualization Techniques: A Case of Digital and Data Curation","year":2019,"lang":"en","type":"article","venue":"International Journal of Digital Curation","topic":"Research Data Management Practices","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Digital curation; Data curation; Syllabus; Computer science; Curriculum; Data science; Context (archaeology); Latent Dirichlet allocation; Metadata; Topic model; Cyberinfrastructure; World Wide Web; Visualization; Data management; Information retrieval; Database; Data mining","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.007319909,0.000340802,0.0004614227,0.01354482,0.00221943,0.003353257,0.000669614,0.001041341,0.001762303],"category_scores_gemma":[0.02504442,0.0003479501,0.0006600866,0.01619252,0.001243965,0.003589553,0.002418752,0.0009343944,0.0003221326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001789258,"about_ca_system_score_gemma":0.001738935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009703952,"about_ca_topic_score_gemma":0.011919,"domain_scores_codex":[0.9944166,0.002754002,0.0004208426,0.0008763646,0.001040185,0.0004920099],"domain_scores_gemma":[0.9575427,0.03083532,0.004676598,0.003007988,0.002873502,0.00106389],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004270941,0.0004294569,0.4618886,0.001075098,0.0001153272,0.003465177,0.2004473,0.005493752,0.01393278,0.02630391,0.00715579,0.2792657],"study_design_scores_gemma":[0.00006762395,0.0002596104,0.5811206,0.0007597129,0.0002393238,0.004140066,0.1627455,0.1081688,0.01386696,0.02507115,0.1033348,0.0002258642],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9400627,0.001053916,0.04692591,0.001477754,0.00003933891,0.0001791898,0.001490709,0.0004452784,0.00832517],"genre_scores_gemma":[0.9585685,0.0003760119,0.03826019,0.00006749066,0.00004093774,0.0001836372,0.001013257,0.0001078473,0.001382223],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9966468,"threshold_uncertainty_score":0.03871185,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1482718394189735,"score_gpt":0.4454172668164202,"score_spread":0.2971454273974466,"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."}}