Privacy-Preserving and Scalable Affect Detection in Online Synchronous Learning

Felix Böttger*, Ufuk Cetinkaya, Daniele Di Mitri, Sebastian Gombert, Krist Shingjergji, Deniz Iren, Roland Klemke

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference Article in proceedingAcademicpeer-review

122 Downloads (Pure)

Abstract

The recent pandemic has forced most educational institutions to shift to distance learning. Teachers can perceive various non-verbal cues in face-to-face classrooms and thus notice when students are distracted, confused, or tired. However, the students’ non-verbal cues are not observable in online classrooms. The lack of these cues poses a challenge for the teachers and hinders them in giving adequate, timely feedback in online educational settings. This can lead to learners not receiving proper guidance and may cause them to be demotivated. This paper proposes a pragmatic approach to detecting student affect in online synchronized learning classrooms. Our approach consists of a method and a privacy-preserving prototype that only collects data that is absolutely necessary to compute action units and is highly scalable by design to run on multiple devices without specialized hardware. We evaluated our prototype using a benchmark for the system performance. Our results confirm the feasibility and the applicability of the proposed approach.

Original languageEnglish
Title of host publicationEducating for a New Future
Subtitle of host publicationMaking Sense of Technology-Enhanced Learning Adoption - 17th European Conference on Technology Enhanced Learning, EC-TEL 2022, Proceedings
EditorsIsabel Hilliger, Pedro J. Muñoz-Merino, Tinne De Laet, Alejandro Ortega-Arranz, Tracie Farrell
Place of PublicationCham
PublisherSpringer, Cham
Pages45-58
Number of pages14
Volume13450
Edition1
ISBN (Electronic)978-3-031-16290-9
ISBN (Print)978-3-031-16289-3
DOIs
Publication statusPublished - 5 Sept 2022
Event17th European Conference on Technology Enhanced Learning - Toulouse, France
Duration: 12 Sept 202216 Sept 2022

Publication series

SeriesSpringer Lecture Notes in Computer Science (LNCS)
Volume13450
ISSN0302-9743

Conference

Conference17th European Conference on Technology Enhanced Learning
Abbreviated titleEC-TEL2022
Country/TerritoryFrance
CityToulouse
Period12/09/2216/09/22

Keywords

  • Action units
  • Affect detection
  • Emotion recognition
  • Privacy
  • TRUSTWORTHY_AI

Fingerprint

Dive into the research topics of 'Privacy-Preserving and Scalable Affect Detection in Online Synchronous Learning'. Together they form a unique fingerprint.

Cite this