{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.01887998,0.001180714,0.001243065,0.03440057,0.001886547,0.005434392,0.001556558,0.001276594,0.003985377],"category_scores_gemma":[0.04712421,0.0006438724,0.002645427,0.02279738,0.0009358234,0.003162225,0.002346767,0.00155167,0.003344898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003007625,"about_ca_system_score_gemma":0.007212266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004024578,"about_ca_topic_score_gemma":0.00904972,"domain_scores_codex":[0.9841737,0.005016466,0.002837378,0.003018069,0.004596835,0.0003577084],"domain_scores_gemma":[0.9607345,0.01722154,0.006178908,0.002019549,0.01318036,0.0006651284],"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":[0.0006153803,0.0004097508,0.04094483,0.008155264,0.001229863,0.0005618905,0.008775815,0.003306284,0.02779797,0.01236217,0.02736127,0.8684795],"study_design_scores_gemma":[0.0008744688,0.001727298,0.2134163,0.003510072,0.00378147,0.003905147,0.0234424,0.1396661,0.04585735,0.0866776,0.4760573,0.001084405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08523367,0.009307036,0.8330137,0.005397012,0.0008951256,0.02449526,0.024371,0.004960033,0.01232714],"genre_scores_gemma":[0.1186709,0.001873091,0.8378665,0.0004696906,0.0003820572,0.02559402,0.009803977,0.0002410103,0.005098669],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9655994,"threshold_uncertainty_score":0.09984809,"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."}}