TY - GEN
T1 - Modeling Simultaneous Preferences for Age, Gender, Race, and Professional Profiles in Government-Expense Spending
T2 - 9th AAAI Conference on Human Computation and Crowdsourcing, HCOMP 2021
AU - Ibrahim, Lujain
AU - Ghassemi, Mohammad M.
AU - Alhanai, Tuka
N1 - Publisher Copyright:
© 2021, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2021
Y1 - 2021
N2 - Bias can have devastating outcomes on everyday life, and may manifest in subtle preferences for particular attributes (age, gender, race, 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.
AB - Bias can have devastating outcomes on everyday life, and may manifest in subtle preferences for particular attributes (age, gender, race, 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.
UR - http://www.scopus.com/inward/record.url?scp=85175819998&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85175819998&partnerID=8YFLogxK
U2 - 10.1609/hcomp.v9i1.18942
DO - 10.1609/hcomp.v9i1.18942
M3 - Conference contribution
AN - SCOPUS:85175819998
SN - 9781577358725
T3 - Proceedings of the AAAI Conference on Human Computation and Crowdsourcing
SP - 84
EP - 96
BT - HCOMP 2021 - Proceedings of the 9th AAAI Conference on Human Computation and Crowdsourcing
A2 - Kamar, Ece
A2 - Luther, Kurt
PB - Association for the Advancement of Artificial Intelligence
Y2 - 14 November 2021 through 18 November 2021
ER -