Suppr超能文献

推荐信中基于性别的语言差异。

Gender-based Language Differences in Letters of Recommendation.

作者信息

Fu Sunyang, Calley Darren Q, Rasmussen Veronica A, Hamilton Marissa D, Lee Christopher K, Kalla Austin, Liu Hongfang

机构信息

Department of AI and Informatics, Mayo Clinic, Rochester, MN.

Department of Physical Medicine and Rehabilitation, Mayo Clinic, Rochester, MN.

出版信息

AMIA Jt Summits Transl Sci Proc. 2023 Jun 16;2023:196-205. eCollection 2023.

Abstract

Gender stereotyping is the practice of assigning or ascribing specific characteristics, differences, or identities to a person solely based on their gender. Biased conceptions of gender can create barriers to equality and need to be proactively identified and addressed. In biomedical education, letters of recommendation (LOR) are considered an important source for evaluating candidates' past performance. Because LOR is subjective and has no standard formatting requirements for the writer, potential language bias can be introduced. Natural language processing (NLP) offers a promising solution to detect language bias in LOR through automatic extraction of sensitive language and identification of letters with strong biases. In our study, we developed, evaluated, and deployed four NLP different methods (sublanguage analysis, dictionary-based approach, rule-based approach, and deep learning approach) for the extraction of psycholinguistics and thematic characteristics in LORs from three different physical therapy residency programs (Neurologic, Orthopaedic, and Sport) at Mayo Clinic. The evaluation statistics suggest that both MedTaggerIE model and Bidirectional Encoder Representations from Transformers model achieved moderate-high performance across eight different thematic categories. Through the pilot demonstration study, we learned that male writers were more likely to use the words 'intelligence', 'exceptional', and 'pursue' and male applicants were more likely to have the words 'strength', 'interpersonal skills', 'conversations', and 'pursue' in their letters of recommendation. Thematic analysis suggested that male and female writers have significant differences in expressing doubt, motivation, and recommendation. Findings derived from the study needed to be carefully interpreted based on the context of the study setting, residency programs, and data. A follow-up demonstration study is needed to further evaluate and interpret the findings.

摘要

性别刻板印象是指仅根据一个人的性别就赋予或归因于其特定特征、差异或身份的做法。有偏见的性别观念会给平等带来障碍,需要积极地加以识别和解决。在生物医学教育中,推荐信被认为是评估候选人过去表现的重要来源。由于推荐信具有主观性,且对撰写者没有标准的格式要求,因此可能会引入潜在的语言偏见。自然语言处理(NLP)提供了一个有前景的解决方案,通过自动提取敏感语言和识别有强烈偏见的信件来检测推荐信中的语言偏见。在我们的研究中,我们开发、评估并部署了四种不同的NLP方法(子语言分析、基于词典的方法、基于规则的方法和深度学习方法),用于从梅奥诊所三个不同的物理治疗住院医师项目(神经科、骨科和运动科)的推荐信中提取心理语言学和主题特征。评估统计表明,MedTaggerIE模型和来自Transformer的双向编码器表征模型在八个不同的主题类别中均取得了中高水平的表现。通过试点示范研究,我们了解到男性撰写者更有可能使用“智力”“杰出”和“追求”等词,而男性申请者的推荐信中更有可能出现“力量”“人际交往能力”“对话”和“追求”等词。主题分析表明,男性和女性撰写者在表达怀疑、动机和推荐方面存在显著差异。需要根据研究背景、住院医师项目和数据对该研究得出的结果进行仔细解读。需要进行后续的示范研究来进一步评估和解读这些结果。

相似文献

1
Gender-based Language Differences in Letters of Recommendation.
AMIA Jt Summits Transl Sci Proc. 2023 Jun 16;2023:196-205. eCollection 2023.
2
Assessment of Gender Differences in Letters of Recommendation for Physical Therapy Residency Applications.
J Phys Ther Educ. 2024 Dec 1;38(4):331-339. doi: 10.1097/JTE.0000000000000337. Epub 2024 Apr 19.
3
Words Used in Letters of Recommendation for Pediatric Residency Applicants: Demographic Differences and Impact on Interviews.
Acad Pediatr. 2023 Nov-Dec;23(8):1614-1619. doi: 10.1016/j.acap.2023.02.012. Epub 2023 Mar 6.
4
Are There Gender-based Differences in Language in Letters of Recommendation to an Orthopaedic Surgery Residency Program?
Clin Orthop Relat Res. 2020 Jul;478(7):1400-1408. doi: 10.1097/CORR.0000000000001053.
5
Assessment of gender differences in letters of recommendation for pharmacy residency applicants.
Am J Health Syst Pharm. 2021 Jun 7;78(12):1118-1125. doi: 10.1093/ajhp/zxab150.
6
Do gender differences exist in letters of recommendation for reproductive endocrinology and infertility fellowship?
Fertil Steril. 2023 Dec;120(6):1234-1242. doi: 10.1016/j.fertnstert.2023.09.018. Epub 2023 Sep 28.
7
Race- and Gender-Based Differences in Descriptions of Applicants in the Letters of Recommendation for Orthopaedic Surgery Residency.
JB JS Open Access. 2020 Jun 26;5(3). doi: 10.2106/JBJS.OA.20.00023. eCollection 2020 Jul-Sep.
8
Use of artificial intelligence for gender bias analysis in letters of recommendation for general surgery residency candidates.
Am J Surg. 2021 Dec;222(6):1051-1059. doi: 10.1016/j.amjsurg.2021.09.034. Epub 2021 Oct 2.
9
Letters of recommendation for pediatric surgery fellowship: Analysis of linguistic differences based on gender of the applicant.
J Pediatr Surg. 2021 Aug;56(8):1299-1304. doi: 10.1016/j.jpedsurg.2021.02.049. Epub 2021 Mar 4.
10
Examining Implicit Bias Differences in Pediatric Surgical Fellowship Letters of Recommendation Using Natural Language Processing.
J Surg Educ. 2023 Apr;80(4):547-555. doi: 10.1016/j.jsurg.2022.12.002. Epub 2022 Dec 17.

本文引用的文献

1
Clinical concept extraction: A methodology review.
J Biomed Inform. 2020 Sep;109:103526. doi: 10.1016/j.jbi.2020.103526. Epub 2020 Aug 6.
2
Assessment of the impact of EHR heterogeneity for clinical research through a case study of silent brain infarction.
BMC Med Inform Decis Mak. 2020 Mar 30;20(1):60. doi: 10.1186/s12911-020-1072-9.
3
Gender-based differences in letters of recommendation written for ophthalmology residency applicants.
BMC Med Educ. 2019 Dec 30;19(1):476. doi: 10.1186/s12909-019-1910-6.
4
Desiderata for delivering NLP to accelerate healthcare AI advancement and a Mayo Clinic NLP-as-a-service implementation.
NPJ Digit Med. 2019 Dec 17;2:130. doi: 10.1038/s41746-019-0208-8. eCollection 2019.
5
Are There Gender-based Differences in Language in Letters of Recommendation to an Orthopaedic Surgery Residency Program?
Clin Orthop Relat Res. 2020 Jul;478(7):1400-1408. doi: 10.1097/CORR.0000000000001053.
6
Can Gender-Fair Language Reduce Gender Stereotyping and Discrimination?
Front Psychol. 2016 Feb 2;7:25. doi: 10.3389/fpsyg.2016.00025. eCollection 2016.
7
An information extraction framework for cohort identification using electronic health records.
AMIA Jt Summits Transl Sci Proc. 2013 Mar 18;2013:149-53. eCollection 2013.
8
Physicians and implicit bias: how doctors may unwittingly perpetuate health care disparities.
J Gen Intern Med. 2013 Nov;28(11):1504-10. doi: 10.1007/s11606-013-2441-1. Epub 2013 Apr 11.
9
Assessing implicit gender bias in Medical Student Performance Evaluations.
Eval Health Prof. 2010 Sep;33(3):365-85. doi: 10.1177/0163278710375097.
10
Gender and letters of recommendation for academia: agentic and communal differences.
J Appl Psychol. 2009 Nov;94(6):1591-9. doi: 10.1037/a0016539.

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验