RCEA: Real-time, Continuous Emotion Annotation for Collecting Precise Mobile Video Ground Truth Labels

要旨

Collecting accurate and precise emotion ground truth labels for mobile video watching is essential for ensuring meaningful predictions. However, video-based emotion annotation techniques either rely on post-stimulus discrete self-reports, or allow real-time, continuous emotion annotations (RCEA) only for desktop settings. Following a user-centric approach, we designed an RCEA technique for mobile video watching, and validated its usability and reliability in a controlled, indoor (N=12) and later outdoor (N=20) study. Drawing on physiological measures, interaction logs, and subjective workload reports, we show that (1) RCEA is perceived to be usable for annotating emotions while mobile video watching, without increasing users' mental workload (2) the resulting time-variant annotations are comparable with intended emotion attributes of the video stimuli (classification error for valence: 8.3%; arousal: 25%). We contribute a validated annotation technique and associated annotation fusion method, that is suitable for collecting fine-grained emotion annotations while users watch mobile videos.

キーワード
emotion
annotation
mobile
video
real-time
continuous
labels
著者
Tianyi Zhang
Centrum Wiskunde & Informatica and Delft University of Technology, Amsterdam & Delft, Netherlands
Abdallah El Ali
Centrum Wiskunde & Informatica (CWI), Amsterdam, Netherlands
Chen Wang
Xinhuanet, Beijing, China
Alan Hanjalic
Delft University of Technology, Delft, Netherlands
Pablo Cesar
Centrum Wiskunde & Informatica and Delft University of Technology, Amsterdam & Delft, Netherlands
DOI

10.1145/3313831.3376808

動画

会議: CHI 2020

The ACM CHI Conference on Human Factors in Computing Systems

セッション: Human factors in design

Paper session
Paper
316C MAUI
2020-04-27 23:00:00
2020-04-28 00:15:00
日本語まとめ
読み込み中…