{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004159798,0.001231847,0.0009976198,0.003599072,0.0009475906,0.003413902,0.002248816,0.001284656,0.004602183],"category_scores_gemma":[0.02682796,0.0009304911,0.002199941,0.004199039,0.00310881,0.008011456,0.004458851,0.004096296,0.001300342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001542588,"about_ca_system_score_gemma":0.001907649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006425965,"about_ca_topic_score_gemma":0.006794915,"domain_scores_codex":[0.9971563,0.001739412,0.0001555826,0.0004659395,0.0003918096,0.00009095328],"domain_scores_gemma":[0.9920548,0.005787101,0.0004374079,0.0009944165,0.000561115,0.0001651249],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009896181,0.00006164212,0.00227772,0.0002252969,0.0001951593,0.00009805348,0.001396574,0.08736521,0.001016672,0.6462542,0.004671749,0.2563388],"study_design_scores_gemma":[0.0000178482,0.00002001473,0.0002829843,0.00005208864,0.0000299847,0.00006498171,0.0001410447,0.4050152,0.0005543212,0.5875134,0.006277348,0.00003067014],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001485848,0.0001047535,0.9972991,0.0002227788,0.00002994566,0.00002246864,0.00008745935,0.0001913971,0.0005561823],"genre_scores_gemma":[0.1028384,0.0005240971,0.8925959,0.0002556872,0.0001408816,0.0004146356,0.0005861632,0.0003326497,0.002311487],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006425965,"threshold_uncertainty_score":0.02199936,"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."}}