Abstract—Educational theories and empirical researches
indicate that teaching objectives are not limited to the field of
knowledge and cognition, and emotion has also proved to be an
important part of learning outcomes and future achievements.
An affective arousal evaluation system focusing on the
self-system goal of education is proposed in this paper, which
introduces artificial intelligence (AI) techniques to evaluate
affective arousal level as a part of teaching quality in the form of
quantitative indicators. The system embeds facial expression
recognition and speech emotion recognition methods, which
extract and analyze the video streaming collected by the
ubiquitous web cameras from both teacher side and student
side during the online teaching process. The experiment verifies
the correlation and Granger causality between teacher-student
affective sequences. The implementation of the system realizes
the output of three quantitative indicators: “Affective
Frequency Index”, “Affective Correlation Index” and
“Affective Arousal Level”.
Index Terms—Affective arousal, expression recognition, speech emotion recognition, teaching evaluation.
The authors are with Department of Electronic Engineering, Fudan University, Shanghai, China (e-mail: firstname.lastname@example.org, email@example.com).
Cite: Jingjing Liu and Xiaofeng Wu, "Prototype of Educational Affective Arousal Evaluation System Based on Facial and Speech Emotion Recognition," International Journal of Information and Education Technology vol. 9, no. 9, pp. 645-651, 2019.Copyright © 2019 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).