{"id":"W2783136253","doi":"10.3758/s13428-017-1009-0","title":"When is best-worst best? A comparison of best-worst scaling, numeric estimation, and rating scales for collection of semantic norms","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":57,"is_retracted":false,"has_abstract":false,"ca_institutions":"Athabasca University; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Concreteness; Computer science; Best practice; Scaling; Generalizability theory; Norm (philosophy); Valence (chemistry); Natural language processing; Psychology; Scale (ratio); Data collection; Cognitive psychology; Artificial intelligence; Statistics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.004495426,0.0002170132,0.0005966943,0.0005953382,0.0004777239,0.00006604406,0.0002622123,0.0002426494,0.0005095207],"category_scores_gemma":[0.001075398,0.0001963801,0.0001382241,0.0009240015,0.00077192,0.0001631497,0.0001069633,0.0003526225,0.00003702644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006107766,"about_ca_system_score_gemma":0.00008653162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002429352,"about_ca_topic_score_gemma":0.0002791806,"domain_scores_codex":[0.9960867,0.001459036,0.0007947308,0.0005380537,0.0005839213,0.0005375674],"domain_scores_gemma":[0.996587,0.001189173,0.0003463698,0.0004733403,0.001248834,0.0001552511],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005960638,0.002277234,0.06290685,0.0004925408,0.0001474923,0.000004872432,0.03820975,0.00000215697,0.06579365,0.0004988966,0.002014751,0.8270558],"study_design_scores_gemma":[0.009844948,0.01729676,0.09090348,0.002022831,0.002331922,0.0001767982,0.09827704,0.0347238,0.7133011,0.02593514,0.003257258,0.001928911],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8752583,0.001050871,0.1206267,0.00009744539,0.0003394861,0.001515348,0.0000487843,0.00002973613,0.001033389],"genre_scores_gemma":[0.7830165,0.00003042332,0.2147666,0.00001497272,0.0001640619,0.0005805691,0.000034365,0.00004651445,0.001346019],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8251268,"threshold_uncertainty_score":0.8008149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2378597029743194,"score_gpt":0.5684250069755211,"score_spread":0.3305653040012018,"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."}}