Age Bias in Emotion Detection: An Analysis of Facial Emotion Recognition Performance on Young, Middle-Aged, and Older Adults

被引:43
作者
Kim, Eugenia [1 ]
Bryant, De'Aira [1 ]
Srikanth, Deepak [1 ]
Howard, Ayanna [1 ]
机构
[1] Georgia Inst Technol, Atlanta, GA 30332 USA
来源
AIES '21: PROCEEDINGS OF THE 2021 AAAI/ACM CONFERENCE ON AI, ETHICS, AND SOCIETY | 2021年
关键词
ethical computing; age bias; facial emotion recognition; technology audit; artificial intelligence; EXPRESSIONS; WOMEN; FACE;
D O I
10.1145/3461702.3462609
中图分类号
TP18 [人工智能理论];
学科分类号
140502 [人工智能];
摘要
The growing potential for facial emotion recognition (FER) technology has encouraged expedited development at the cost of rigorous validation. Many of its use-cases may also impact the diverse global community as FER becomes embedded into domains ranging from education to security to healthcare. Yet, prior work has highlighted that FER can exhibit both gender and racial biases like other facial analysis techniques. As a result, bias-mitigation research efforts have mainly focused on tackling gender and racial disparities, while other demographic related biases, such as age, have seen less progress. This work seeks to examine the performance of state of the art commercial FER technology on expressive images of men and women from three distinct age groups. We utilize four different commercial FER systems in a black box methodology to evaluate how six emotions - anger, disgust, fear, happiness, neutrality, and sadness - are correctly detected by age group. We further investigate how algorithmic changes over the last year have affected system performance. Our results found that all four commercial FER systems most accurately perceived emotion in images of young adults and least accurately in images of older adults. This trend was observed for analyses conducted in 2019 and 2020. However, little to no gender disparities were observed in either year. While older adults may not have been the initial target consumer of FER technology, statistics show the demographic is quickly growing more keen to applications that use such systems. Our results demonstrate the importance of considering various demographic subgroups during FER system validation and the need for inclusive, intersectional algorithmic developmental practices.
引用
收藏
页码:638 / 644
页数:7
相关论文
共 41 条
[1]
Agrawal, 2020, AUTOMATICALLY DETECT
[2]
Amazon, 2020, WHAT IS AM REK
[3]
Amazon Rekognition, 2019, AM REK IMPR FAC AN
[4]
Andelic Nicole, 2018, INT CONF PERVAS COMP, DOI 10.1109/PERCOMW.2018.8480127
[5]
[Anonymous], 2019, AAAIACM C ETHICS SOC, DOI DOI 10.1145/3306618.3314284
[6]
Towards More Robust Automatic Facial Expression Recognition in Smart Environments [J].
Bernin, Arne ;
Mueller, Larissa ;
Ghose, Sobin ;
von Luck, Kai ;
Grecos, Christos ;
Wang, Qi ;
Vogt, Florian .
10TH ACM INTERNATIONAL CONFERENCE ON PERVASIVE TECHNOLOGIES RELATED TO ASSISTIVE ENVIRONMENTS (PETRA 2017), 2017, :37-44
[7]
Buolamwini J., 2018, P 1 C FAIRN ACC TRAN, P77
[8]
Age-Dependent Face Detection and Face Categorization Performance [J].
Carbon, Claus-Christian ;
Grueter, Martina ;
Grueter, Thomas .
PLOS ONE, 2013, 8 (10)
[9]
Cheng J, 2013, PROCEEDINGS OF THE 2013 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE FOR ENGINEERING SOLUTIONS (CIES), P1, DOI 10.1109/CIES.2013.6611721
[10]
Darwin C., 1872, P374