{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1732652,0.001002857,0.002442636,0.005902025,0.002207639,0.007149955,0.003269828,0.00189054,0.004211255],"category_scores_gemma":[0.5232766,0.0008041553,0.002542096,0.005118758,0.005587887,0.01045989,0.004379515,0.00316779,0.0009718807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002955474,"about_ca_system_score_gemma":0.00349828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002177262,"about_ca_topic_score_gemma":0.004803327,"domain_scores_codex":[0.8137521,0.1237287,0.01798096,0.008182772,0.03497139,0.001384011],"domain_scores_gemma":[0.4986916,0.3674884,0.02511889,0.04473548,0.06049481,0.003470749],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.008605566,0.001111521,0.1380224,0.003499122,0.002196083,0.0001235199,0.02399597,0.003999493,0.003498822,0.127174,0.03360535,0.6541681],"study_design_scores_gemma":[0.001794726,0.007284918,0.435675,0.007342913,0.003288273,0.001668234,0.03648732,0.07627588,0.01352976,0.30775,0.1069078,0.001995264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3193654,0.01081968,0.5955104,0.007026834,0.004226321,0.003974127,0.003493543,0.001913855,0.05366979],"genre_scores_gemma":[0.6797738,0.001846663,0.3093882,0.0007094188,0.0003797688,0.003843231,0.001962359,0.0009348057,0.001161763],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8267348,"threshold_uncertainty_score":0.916325,"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."}}