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

会議: CHI 2020

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2020.acm.org/)

セッション: Emotion, personality & identity

Paper session
316C MAUI
5 件の発表
2020-04-29 20:00:00
2020-04-29 21:15:00
日本語まとめ
読み込み中…