D66. Linguistic Analysis of Race and Gender Bias in Narrative Letters of Recommendation for Plastic Surgery Residency Applicants

PURPOSE: It has previously been shown that gender bias exists in standardized letters of recommendation for plastic surgery residency. However, similar analysis has not been conducted for narrative letters of recommendation (NLORs). Therefore, this study aims to determine if there exists linguistic bias in NLORs for plastic surgery residency based on applicants' and writers' gender and race. METHODS: The sample included applicants to a 6-year integrated plastic surgery residency program within application cycles from 2021-2023. Exclusion criteria included reapplicants and applicants without NLORs. Applicant demographics were self-identified. Faculty gender was identified through public online platforms and faculty race through Namsor, a validated artificial intelligence software for name classification. The Linguistic Inquiry and Word Count program was used to calculate the amount of words in each NLOR that fell within predetermined linguistic categories, such as Power, Achievement, and Social Behavior. Descriptive statistics and t-tests were used in analysis where appropriate. RESULTS: 626 unique applicants had at least one NLOR. Female writers used more words describing applicants' social and emotional qualities compared to male writers. White writers used more words conveying Negative Tone to describe Non-white applicants. Non-white writers used more words describing accomplishment, drive, and social qualities of Non-white applicants compared to White applicants. CONCLUSION: Analysis of NLORs revealed differences related to gender and race. Female writers produced more favorable recommendations than male writers. Racial discordance between writer and applicant resulted in differences in letter quality. Faculty education to improve the objectivity of NLORs is necessary.