{"id":"W3135850294","doi":"10.1145/3408877.3432369","title":"The Role of Race and Gender in Teaching Evaluation of Computer Science Professors: A Large Scale Analysis on RateMyProfessor Data","year":2021,"lang":"en","type":"article","venue":"","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trent University","funders":"","keywords":"Quality (philosophy); Race (biology); Scale (ratio); Personality; Computer science; Psychology; Mathematics education; Social psychology; Sociology","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006434855,0.0002360753,0.0004732601,0.002526272,0.0006196608,0.0007033555,0.000520925,0.0003624161,0.002645479],"category_scores_gemma":[0.02424663,0.0001459718,0.0004908915,0.002503767,0.0005189718,0.000700812,0.001026012,0.0004342358,0.0009690929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000389498,"about_ca_system_score_gemma":0.0003523607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003034592,"about_ca_topic_score_gemma":0.004572549,"domain_scores_codex":[0.9940288,0.002601428,0.0005416237,0.0007308344,0.001617314,0.0004798692],"domain_scores_gemma":[0.9511158,0.02033646,0.01704936,0.004141397,0.004454236,0.002902837],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001063754,0.00005719944,0.9933298,0.00001988877,0.00004854695,0.00003179926,0.0009491945,0.00003520778,0.0002535574,0.00004686361,0.0004387077,0.004682736],"study_design_scores_gemma":[0.000003375936,0.00005749663,0.998225,0.000006161417,0.00001108816,0.00005245277,0.0007894877,0.0001501185,0.000151511,0.0000153747,0.0005339208,0.00000400479],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.99761,0.0001052249,0.0002605605,0.00005165132,0.000007891084,0.00002167604,0.001122852,0.00000761117,0.0008126189],"genre_scores_gemma":[0.998071,0.00004198572,0.0002025509,0.00002219195,0.00001749761,0.00005512943,0.001146918,0.00001034815,0.0004324199],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9935651,"threshold_uncertainty_score":0.03403121,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2376498457698903,"score_gpt":0.5169678430688488,"score_spread":0.2793179972989586,"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."}}