Abstract

Language learning anxiety is one of the most important affective variables affecting the effect of language learning. Sensor technologies involve devices that generate a digital output based on the detection of some physical phenomenon in terms of events or changes in a relevant environment. In this work, we propose an effective computing model. Through the research on the classification of emotions and dimensional space theory, combined with the actual learning emotions of learners in the flipped classroom teaching mode, it proposes the avoidance degree based on face detection and the concentration degree based on eyelid detection. Experiments show that our multi-task affective computing method can effectively characterize students' anxiety, and can even be extended to more emotions, outperforming single-task baseline models.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call