AI bias in Human-Robot Interaction: An evaluation of the Risk in Gender Biased Robots

Tom Hitron; Benny Megidish; Etay Todress; Noa Morag; Hadas Erel

doi:10.1109/RO-MAN53752.2022.9900673

AI bias in Human-Robot Interaction: An evaluation of the Risk in Gender Biased Robots

Tom Hitron
, Benny Megidish
, Etay Todress
, Noa Morag
, Hadas Erel

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

19 Scopus citations

Abstract

With recent advancements in AI, there are growing concerns about human biases implemented in AI decisions. Threats posed by AI bias may be even more drastic when applied to robots that are perceived as independent entities and are not mediated by humans. Furthermore, technology is typically perceived as objective and there is a risk that people will embrace its decisions without considering possible biases. In order to understand the extent of threats brought about by such biases, we evaluated participants' responses to a gender-biased robot mediating a debate between two participants (male and female). The vast majority of participants did not associate the robot's behavior with a bias, despite being informed that the robot's algorithm is based on human examples. Participants attributed the robot's decisions to their own performance and used explanations involving gender stereotypes. Our findings suggest that robots' biased behaviors can serve as validation for common human stereotypes.

Original language	English
Title of host publication	RO-MAN 2022 - 31st IEEE International Conference on Robot and Human Interactive Communication
Subtitle of host publication	Social, Asocial, and Antisocial Robots
Publisher	Institute of Electrical and Electronics Engineers
Pages	1598-1605
Number of pages	8
ISBN (Electronic)	9781728188591
DOIs	https://doi.org/10.1109/RO-MAN53752.2022.9900673
State	Published - 1 Jan 2022
Externally published	Yes
Event	31st IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2022 - Napoli, Italy Duration: 29 Aug 2022 → 2 Sep 2022

Publication series

Name	RO-MAN 2022 - 31st IEEE International Conference on Robot and Human Interactive Communication: Social, Asocial, and Antisocial Robots

Conference

Conference	31st IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2022
Country/Territory	Italy
City	Napoli
Period	29/08/22 → 2/09/22

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 5 Gender Equality

ASJC Scopus subject areas

Human-Computer Interaction
Social Psychology
Communication
Artificial Intelligence
Computer Science Applications

Access to Document

10.1109/RO-MAN53752.2022.9900673

Cite this

Hitron, T., Megidish, B., Todress, E., Morag, N., & Erel, H. (2022). AI bias in Human-Robot Interaction: An evaluation of the Risk in Gender Biased Robots. In RO-MAN 2022 - 31st IEEE International Conference on Robot and Human Interactive Communication: Social, Asocial, and Antisocial Robots (pp. 1598-1605). (RO-MAN 2022 - 31st IEEE International Conference on Robot and Human Interactive Communication: Social, Asocial, and Antisocial Robots). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/RO-MAN53752.2022.9900673

Hitron, Tom ; Megidish, Benny ; Todress, Etay et al. / AI bias in Human-Robot Interaction : An evaluation of the Risk in Gender Biased Robots. RO-MAN 2022 - 31st IEEE International Conference on Robot and Human Interactive Communication: Social, Asocial, and Antisocial Robots. Institute of Electrical and Electronics Engineers, 2022. pp. 1598-1605 (RO-MAN 2022 - 31st IEEE International Conference on Robot and Human Interactive Communication: Social, Asocial, and Antisocial Robots).

@inproceedings{bc5cb8c4f38c47478306f75043875f58,

title = "AI bias in Human-Robot Interaction: An evaluation of the Risk in Gender Biased Robots",

abstract = "With recent advancements in AI, there are growing concerns about human biases implemented in AI decisions. Threats posed by AI bias may be even more drastic when applied to robots that are perceived as independent entities and are not mediated by humans. Furthermore, technology is typically perceived as objective and there is a risk that people will embrace its decisions without considering possible biases. In order to understand the extent of threats brought about by such biases, we evaluated participants' responses to a gender-biased robot mediating a debate between two participants (male and female). The vast majority of participants did not associate the robot's behavior with a bias, despite being informed that the robot's algorithm is based on human examples. Participants attributed the robot's decisions to their own performance and used explanations involving gender stereotypes. Our findings suggest that robots' biased behaviors can serve as validation for common human stereotypes.",

author = "Tom Hitron and Benny Megidish and Etay Todress and Noa Morag and Hadas Erel",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 31st IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2022 ; Conference date: 29-08-2022 Through 02-09-2022",

year = "2022",

month = jan,

day = "1",

doi = "10.1109/RO-MAN53752.2022.9900673",

language = "English",

series = "RO-MAN 2022 - 31st IEEE International Conference on Robot and Human Interactive Communication: Social, Asocial, and Antisocial Robots",

publisher = "Institute of Electrical and Electronics Engineers",

pages = "1598--1605",

booktitle = "RO-MAN 2022 - 31st IEEE International Conference on Robot and Human Interactive Communication",

address = "United States",

}

Hitron, T, Megidish, B, Todress, E, Morag, N & Erel, H 2022, AI bias in Human-Robot Interaction: An evaluation of the Risk in Gender Biased Robots. in RO-MAN 2022 - 31st IEEE International Conference on Robot and Human Interactive Communication: Social, Asocial, and Antisocial Robots. RO-MAN 2022 - 31st IEEE International Conference on Robot and Human Interactive Communication: Social, Asocial, and Antisocial Robots, Institute of Electrical and Electronics Engineers, pp. 1598-1605, 31st IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2022, Napoli, Italy, 29/08/22. https://doi.org/10.1109/RO-MAN53752.2022.9900673

AI bias in Human-Robot Interaction: An evaluation of the Risk in Gender Biased Robots. / Hitron, Tom; Megidish, Benny; Todress, Etay et al.
RO-MAN 2022 - 31st IEEE International Conference on Robot and Human Interactive Communication: Social, Asocial, and Antisocial Robots. Institute of Electrical and Electronics Engineers, 2022. p. 1598-1605 (RO-MAN 2022 - 31st IEEE International Conference on Robot and Human Interactive Communication: Social, Asocial, and Antisocial Robots).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - AI bias in Human-Robot Interaction

T2 - 31st IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2022

AU - Hitron, Tom

AU - Megidish, Benny

AU - Todress, Etay

AU - Morag, Noa

AU - Erel, Hadas

PY - 2022/1/1

Y1 - 2022/1/1

N2 - With recent advancements in AI, there are growing concerns about human biases implemented in AI decisions. Threats posed by AI bias may be even more drastic when applied to robots that are perceived as independent entities and are not mediated by humans. Furthermore, technology is typically perceived as objective and there is a risk that people will embrace its decisions without considering possible biases. In order to understand the extent of threats brought about by such biases, we evaluated participants' responses to a gender-biased robot mediating a debate between two participants (male and female). The vast majority of participants did not associate the robot's behavior with a bias, despite being informed that the robot's algorithm is based on human examples. Participants attributed the robot's decisions to their own performance and used explanations involving gender stereotypes. Our findings suggest that robots' biased behaviors can serve as validation for common human stereotypes.

AB - With recent advancements in AI, there are growing concerns about human biases implemented in AI decisions. Threats posed by AI bias may be even more drastic when applied to robots that are perceived as independent entities and are not mediated by humans. Furthermore, technology is typically perceived as objective and there is a risk that people will embrace its decisions without considering possible biases. In order to understand the extent of threats brought about by such biases, we evaluated participants' responses to a gender-biased robot mediating a debate between two participants (male and female). The vast majority of participants did not associate the robot's behavior with a bias, despite being informed that the robot's algorithm is based on human examples. Participants attributed the robot's decisions to their own performance and used explanations involving gender stereotypes. Our findings suggest that robots' biased behaviors can serve as validation for common human stereotypes.

UR - https://www.scopus.com/pages/publications/85140722558

U2 - 10.1109/RO-MAN53752.2022.9900673

DO - 10.1109/RO-MAN53752.2022.9900673

M3 - Conference contribution

AN - SCOPUS:85140722558

T3 - RO-MAN 2022 - 31st IEEE International Conference on Robot and Human Interactive Communication: Social, Asocial, and Antisocial Robots

SP - 1598

EP - 1605

BT - RO-MAN 2022 - 31st IEEE International Conference on Robot and Human Interactive Communication

PB - Institute of Electrical and Electronics Engineers

Y2 - 29 August 2022 through 2 September 2022

ER -

Hitron T, Megidish B, Todress E, Morag N, Erel H. AI bias in Human-Robot Interaction: An evaluation of the Risk in Gender Biased Robots. In RO-MAN 2022 - 31st IEEE International Conference on Robot and Human Interactive Communication: Social, Asocial, and Antisocial Robots. Institute of Electrical and Electronics Engineers. 2022. p. 1598-1605. (RO-MAN 2022 - 31st IEEE International Conference on Robot and Human Interactive Communication: Social, Asocial, and Antisocial Robots). doi: 10.1109/RO-MAN53752.2022.9900673

AI bias in Human-Robot Interaction: An evaluation of the Risk in Gender Biased Robots

Abstract

Publication series

Conference

UN SDGs

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this