{"id":"W3041672764","doi":"10.22215/etd/2018-12846","title":"Approach to Identify Topics in a Collection of TIM Review Articles and their Changes Over Time","year":2018,"lang":"en","type":"dissertation","venue":"","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Latent Dirichlet allocation; Topic model; Strengths and weaknesses; Data science; Computer science; Information retrieval; Replicate; Psychology; Statistics; Mathematics","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":[0.0007836472,0.00007277335,0.0002425237,0.0001470433,0.00007285819,0.0000217754,0.00007424127,0.0000738772,0.0003427392],"category_scores_gemma":[0.0001735473,0.00005792344,0.00004542226,0.0006514754,0.00002697027,0.00003754354,0.00001256634,0.00004254933,0.000007959357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002778237,"about_ca_system_score_gemma":0.0000578257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001345118,"about_ca_topic_score_gemma":0.01279998,"domain_scores_codex":[0.9992412,0.0001791375,0.0001692229,0.0001578341,0.0001707231,0.00008190161],"domain_scores_gemma":[0.9996096,0.00007773846,0.00009101683,0.0000579116,0.0001283608,0.00003540122],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001027993,0.0005127907,0.003034378,0.00339239,0.0003127592,8.529712e-7,0.1381148,0.000009092531,0.00161784,0.01626358,0.0418835,0.7947553],"study_design_scores_gemma":[0.001060819,0.0004523795,0.5472392,0.007685663,0.000826048,0.000002352276,0.03174563,0.00814626,0.004286498,0.08228776,0.3141628,0.002104647],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"other","genre_scores_codex":[0.7207018,0.01015274,0.001415739,0.002226283,0.0003563215,0.001455276,0.000008387156,0.00005433728,0.2636291],"genre_scores_gemma":[0.267114,0.02360954,0.0428465,0.002356753,0.001785994,0.0003796903,0.0006897643,0.00007114369,0.6611466],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7926506,"threshold_uncertainty_score":0.7142689,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0579344911101955,"score_gpt":0.4108684704531457,"score_spread":0.3529339793429502,"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."}}