Deep Learning Approach for Identifying Emotions in IELTS Speaking Tests
Abstract— This paper proposes a novel deep learning framework to identify student emotions or affective states in IELTS speaking video tests. This approach has one unique characteristic, it extracts features from a face image and sends it to a deep neural network model for emotion classification. The main objective of this study is to find the correlation between the test takers emotion status and their test grades. This framework is evaluated with extensive experiments. The achieved results show promising performance based on the size of the data and computing resources. The outcomes of this work would add value to OEP systems.
Index Terms— Deep learning, Proctoring, OEP
Lenin Kahanga, Yan Wang
College of Computer Science and Technology, Harbin Engineering University, CHINA
Cite: Lenin Kahanga, Yan Wang, "Deep Learning Approach for Identifying Emotions in IELTS Speaking Tests," Proceedings of 2019 the 9th International Workshop on Computer Science and Engineering, pp. 265-273, Hong Kong, 15-17 June, 2019.