TY - JOUR
T1 - Troi
T2 - Towards understanding users perspectives to mobile automatic emotion recognition system in their natural setting
AU - Dissanayake, Vipula
AU - Tang, Vanessa
AU - Elvitigala, Don Samitha
AU - Wen, Elliott
AU - Wu, Michelle
AU - Nanayakkara, Suranga
N1 - Funding Information:
This work has been supported by the doctoral scholarship of the University of Auckland and the Assistive Augmentation Research Grant through the Entrepreneurial Universities (EU) initiative of New Zealand.
Publisher Copyright:
© 2022 Association for Computing Machinery.
PY - 2022/9/20
Y1 - 2022/9/20
N2 - Emotional Self-Awareness (ESA) plays a vital role in physical and mental well-being. Recent advancements in artificial intelligence technologies have shown promising emotion recognition results, opening new opportunities to build systems to support ESA. However, little research has been done to understand users’ perspectives on artificial-intelligence-based emotion recognition systems. We introduce Troi, an automatic emotion recognition mobile app using wearable signals. With Troi, we ran a multi-day user study with 12 users to understand user preference parameters, such as perceived accuracy, confidence, preferred emotion representations, effect of self-awareness of emotions, and real-time use cases. Further, we extend our study to evaluate the machine learning model in-the-wild to understand behaviours in-the-wild. We found that users perceived accuracy of the emotion recognition model is higher than the actual model prediction accuracy; there was no strong preference for one specific emotion representation, and users’ self-awareness of emotions improved over time.
AB - Emotional Self-Awareness (ESA) plays a vital role in physical and mental well-being. Recent advancements in artificial intelligence technologies have shown promising emotion recognition results, opening new opportunities to build systems to support ESA. However, little research has been done to understand users’ perspectives on artificial-intelligence-based emotion recognition systems. We introduce Troi, an automatic emotion recognition mobile app using wearable signals. With Troi, we ran a multi-day user study with 12 users to understand user preference parameters, such as perceived accuracy, confidence, preferred emotion representations, effect of self-awareness of emotions, and real-time use cases. Further, we extend our study to evaluate the machine learning model in-the-wild to understand behaviours in-the-wild. We found that users perceived accuracy of the emotion recognition model is higher than the actual model prediction accuracy; there was no strong preference for one specific emotion representation, and users’ self-awareness of emotions improved over time.
KW - Automatic Emotion Recognition
KW - In-the-wild Study
KW - Mobile Application
KW - Physiological Signals
UR - http://www.scopus.com/inward/record.url?scp=85141141380&partnerID=8YFLogxK
U2 - 10.1145/3546738
DO - 10.1145/3546738
M3 - Article
AN - SCOPUS:85141141380
SN - 2573-0142
VL - 6
JO - Proceedings of the ACM on Human-Computer Interaction
JF - Proceedings of the ACM on Human-Computer Interaction
IS - MHCI
M1 - 203
ER -