{"title":"Modeling Simultaneous Preferences for Age, Gender, Race, and Professional Profiles in Government-Expense Spending: A Conjoint Analysis","authors":"Lujain Ibrahim, M. Ghassemi, Tuka Alhanai","doi":"10.1609/hcomp.v9i1.18942","DOIUrl":null,"url":null,"abstract":"Bias can have devastating outcomes on everyday life, and may manifest in subtle preferences for particular attributes (age, gender, ethnicity, profession). Understanding bias is complex, but first requires identifying the variety and interplay of individual preferences. In this study, we deployed a sociotechnical, web-based human-subject experiment to quantify individual preferences in the context of selecting an advisor to successfully pitch a government-expense. We utilized conjoint analysis to rank the preferences of 722 U.S. based subjects, and observed that their ideal advisor was White, middle-aged, and of either a government or STEM-related profession (0.68 AUROC, p < 0.05). The results motivate the simultaneous measurement of preferences as a strategy to offset preferences that may yield negative consequences (e.g. prejudice, disenfranchisement) in contexts where social interests are being represented.","PeriodicalId":87339,"journal":{"name":"Proceedings of the ... AAAI Conference on Human Computation and Crowdsourcing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the ... AAAI Conference on Human Computation and Crowdsourcing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1609/hcomp.v9i1.18942","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Bias can have devastating outcomes on everyday life, and may manifest in subtle preferences for particular attributes (age, gender, ethnicity, profession). Understanding bias is complex, but first requires identifying the variety and interplay of individual preferences. In this study, we deployed a sociotechnical, web-based human-subject experiment to quantify individual preferences in the context of selecting an advisor to successfully pitch a government-expense. We utilized conjoint analysis to rank the preferences of 722 U.S. based subjects, and observed that their ideal advisor was White, middle-aged, and of either a government or STEM-related profession (0.68 AUROC, p < 0.05). The results motivate the simultaneous measurement of preferences as a strategy to offset preferences that may yield negative consequences (e.g. prejudice, disenfranchisement) in contexts where social interests are being represented.
偏见会对日常生活造成毁灭性的后果,并可能表现为对特定属性(年龄、性别、种族、职业)的微妙偏好。理解偏见是复杂的,但首先需要确定个体偏好的多样性和相互作用。在这项研究中,我们部署了一个社会技术、基于网络的人类受试者实验,以量化在选择顾问成功推销政府支出的背景下的个人偏好。我们利用联合分析对722名美国受试者的偏好进行排序,并观察到他们理想的顾问是白人,中年,政府或stem相关专业(0.68 AUROC, p < 0.05)。这些结果促使人们同时测量偏好,作为一种策略,以抵消在代表社会利益的情况下可能产生负面后果(如偏见、剥夺公民权)的偏好。