Emotion, personality & identity

Paper session

会議の名前
CHI 2020
Heartbeats in the Wild: A Field Study Exploring ECG Biometrics in Everyday Life
要旨

This paper reports on an in-depth study of electrocardiogram (ECG) biometrics in everyday life. We collected ECG data from 20 people over a week, using a non-medical chest tracker. We evaluated user identification accuracy in several scenarios and observed equal error rates of 9.15% to 21.91%, heavily depending on 1) the number of days used for training, and 2) the number of heartbeats used per identification decision. We conclude that ECG biometrics can work in the wild but are less robust than expected based on the literature, highlighting that previous lab studies obtained highly optimistic results with regard to real life deployments. We explain this with noise due to changing body postures and states as well as interrupted measures. We conclude with implications for future research and the design of ECG biometrics systems for real world deployments, including critical reflections on privacy.

受賞
Honorable Mention
キーワード
Electrocardiogram
ECG
biometrics
field study
著者
Florian Lehmann
Ludwig Maximilian University of Munich, Munich, Germany
Daniel Buschek
University of Bayreuth, Bayreuth, Germany
DOI

10.1145/3313831.3376536

論文URL

https://doi.org/10.1145/3313831.3376536

Faces of Focus: A Study on the Facial Cues of Attentional States
要旨

Automatically detecting attentional states is a prerequisite for designing interventions to manage attention — knowledge workers' most critical resource. As a first step towards this goal, it is necessary to understand how different attentional states are made discernible through visible cues in knowledge workers. In this paper, we demonstrate the important facial cues to detect attentional states by evaluating a data set of 15 participants that we tracked over a whole workday, which included their challenge and engagement levels. Our evaluation shows that gaze, pitch, and lips part action units are indicators of engaged work; while pitch, gaze movements, gaze angle, and upper-lid raiser action units are indicators of challenging work. These findings reveal a significant relationship between facial cues and both engagement and challenge levels experienced by our tracked participants. Our work contributes to the design of future studies to detect attentional states based on facial cues.

キーワード
Attentional state
Facial Expression
Engagement
Challenge
Focus
著者
Ebrahim Babaei
University of Melbourne, Melbourne, VIC, Australia
Namrata Srivastava
University of Melbourne, Melbourne, VIC, Australia
Joshua Newn
University of Melbourne, Melbourne, VIC, Australia
Qiushi Zhou
University of Melbourne, Melbourne, VIC, Australia
Tilman Dingler
University of Melbourne, Melbourne, VIC, Australia
Eduardo Velloso
University of Melbourne, Melbourne, VIC, Australia
DOI

10.1145/3313831.3376566

論文URL

https://doi.org/10.1145/3313831.3376566

動画
Understanding Users' Perception Towards Automated Personality Detection with Group-specific Behavioral Data
要旨

Thanks to advanced sensing and logging technology, automatic personality assessment (APA) with users' behavioral data in the workplace is on the rise. While previous work has focused on building APA systems with high accuracy, little research has attempted to understand users' perception towards APA systems. To fill this gap, we take a mixed-methods approach: we (1) designed a survey (n=89) to understand users'social workplace behavior both online and offline and their privacy concerns; (2) built a research probe that detects personality from online and offline data streams with up to 81.3% accuracy, and deployed it for three weeks in Korea (n=32); and (3) conducted post-interviews (n=9). We identify privacy issues in sharing data and system-induced change in natural behavior as important design factors for APA systems. Our findings suggest that designers should consider the complex relationship between users' perception and system accuracy for a more user-centered APA design.

キーワード
User Perception
Automatic Personality Assessment (APA)
Tracking
Co-located Group
Privacy
Behavior Change
著者
Seoyoung Kim
Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea
Arti Thakur
University of California, Davis, Davis, CA, USA
Juho Kim
Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea
DOI

10.1145/3313831.3376250

論文URL

https://doi.org/10.1145/3313831.3376250

動画
The Human in Emotion Recognition on Social Media: Attitudes, Outcomes, Risks
要旨

Emotion recognition algorithms recognize, infer, and harvest emotions using data sources such as social media behavior, streaming service use, voice, facial expressions, and biometrics in ways often opaque to the people providing these data. People's attitudes towards emotion recognition and the harms and outcomes they associate with it are important yet unknown. Focusing on social media, we interviewed 13 adult U.S. social media users to fill this gap. We find that people view emotions as insights to behavior, prone to manipulation, intimate, vulnerable, and complex. Many find emotion recognition invasive and scary, associating it with autonomy and control loss. We identify two categories of emotion recognition's risks: individual and societal. We discuss findings' implications for algorithmic accountability and argue for considering emotion data as sensitive. Using a Science and Technology Studies lens, we advocate that technology users should be considered as a relevant social group in emotion recognition advancements.

キーワード
Emotion Recognition
Emotion AI
Social Media
Ethics
Privacy
Fairness
Algorithmic Accountability
AI Ethics
著者
Nazanin Andalibi
University of Michigan – Ann Arbor, Ann Arbor, MI, USA
Justin Buss
University of Michigan – Ann Arbor, Ann Arbor, MI, USA
DOI

10.1145/3313831.3376680

論文URL

https://doi.org/10.1145/3313831.3376680

Emotional Footprints of Email Interruptions
要旨

Working in an environment with constant interruptions is known to affect stress, but how do interruptions affect emotional expression? Emotional expression can have significant impact on interactions among coworkers. We analyzed the video of 26 participants who performed an essay task in a laboratory while receiving either continual email interruptions or receiving a single batch of email. Facial videos of the participants were run through a convolutional neural network to determine the emotional mix via decoding of facial expressions. Using a novel co-occurrence matrix analysis, we showed that with batched email, a neutral emotional state is dominant with sadness being a distant second, and with continual interruptions, this pattern is reversed, and sadness is mixed with fear. We discuss the implications of these results for how interruptions can impact employees' well-being and organizational climate.

キーワード
Email interruptions
emotions
facial expressions
convolutional neural network
co-occurence matrix
著者
Christopher Blank
University of Houston, Houston, TX, USA
Shaila Zaman
University of Houston, Houston, TX, USA
Amanveer Wesley
University of Houston, Houston, TX, USA
Panagiotis Tsiamyrtzis
Politechnico di Milano, Milan, Italy
Dennis R. Da Cunha Silva
Texas A&M University, College Station, TX, USA
Ricardo Gutierrez-Osuna
Texas A&M University, College Station, TX, USA
Gloria Mark
University of California, Irvine, Irvine, CA, USA
Ioannis Pavlidis
University of Houston, Houston, TX, USA
DOI

10.1145/3313831.3376282

論文URL

https://doi.org/10.1145/3313831.3376282

動画