{"id":"W4224311899","doi":"10.1111/cars.12378","title":"A new method for computational cultural cartography: From neural word embeddings to transformers and Bayesian mixture models","year":2022,"lang":"en","type":"article","venue":"Canadian Review of Sociology/Revue canadienne de sociologie","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Latent semantic analysis; Word (group theory); Natural language processing; Linguistics","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":[0.002404261,0.0002221254,0.0006953763,0.0002240812,0.001058924,0.00001849287,0.000446107,0.00017681,0.0003336293],"category_scores_gemma":[0.0005655517,0.0002347345,0.0004220416,0.0004757235,0.0003834465,0.0001048581,0.00004054785,0.0003600774,7.10632e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001033128,"about_ca_system_score_gemma":0.001900109,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1992704,"about_ca_topic_score_gemma":0.3725011,"domain_scores_codex":[0.9970363,0.001031264,0.0004471903,0.0005005028,0.0001120177,0.000872718],"domain_scores_gemma":[0.9970164,0.001292956,0.0001848028,0.0001228032,0.000246586,0.001136436],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00008448603,0.00003714802,0.01265378,0.001111005,0.001140264,0.00004959306,0.2594139,0.03634843,0.00009915502,0.2360244,0.06589232,0.3871456],"study_design_scores_gemma":[0.0009396999,0.0003497073,0.01499225,0.0004656831,0.000767373,0.00002331522,0.09646279,0.02707679,0.000001505673,0.7292238,0.1285169,0.001180117],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4385815,0.06874357,0.3233156,0.1579032,0.001352761,0.004028159,0.00411053,0.0001517042,0.001813066],"genre_scores_gemma":[0.7907278,0.001514908,0.1890123,0.01695406,0.000415681,0.0003603096,0.0007250723,0.00003378937,0.0002560983],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4931995,"threshold_uncertainty_score":0.9572197,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05651616741544198,"score_gpt":0.3614541987538037,"score_spread":0.3049380313383618,"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."}}