Academic Emotion Classification and Recognition Method for Large-scale Online Learning Environment—Based on A-CNN and LSTM-ATT Deep Learning Pipeline Method

International Journal of Environmental Research and Public Health

Yaojia Wei¹  Longhui Qiu¹  Xianglin Pan¹  Yongmei Ma²  Xiang Feng³ 

[1] Department of Educational Information Technology, East China Normal University, Shanghai 200062, China;School of Mathematics and Statistics, Chaohu University, Hefei 238000, China;Shanghai Engineering Research Center of Digital Education Equipment, East China Normal University, Shanghai 200062, China;

关键词: academic emotion;    subjective well-being;    academic emotion classification method;    academic emotion classification algorithm;   

DOI  :  10.3390/ijerph17061941

来源: DOAJ

【 摘 要 】

Subjective well-being is a comprehensive psychological indicator for measuring quality of life. Studies have found that emotional measurement methods and measurement accuracy are important for well-being-related research. Academic emotion is an emotion description in the field of education. The subjective well-being of learners in an online learning environment can be studied by analyzing academic emotions. However, in a large-scale online learning environment, it is extremely challenging to classify learners’ academic emotions quickly and accurately for specific comment aspects. This study used literature analysis and data pre-analysis to build a dimensional classification system of academic emotion aspects for students’ comments in an online learning environment, as well as to develop an aspect-oriented academic emotion automatic recognition method, including an aspect-oriented convolutional neural network (A-CNN) and an academic emotion classification algorithm based on the long short-term memory with attention mechanism (LSTM-ATT) and the attention mechanism. The experiments showed that this model can provide quick and effective identification. The A-CNN model accuracy on the test set was 89%, and the LSTM-ATT model accuracy on the test set was 71%. This research provides a new method for the measurement of large-scale online academic emotions, as well as support for research related to students’ well-being in online learning environments.

【 授权许可】

Unknown