Research on the Method of Identifying Students' Online Emotion Based on ALBERT
Yongmei Ren, Xiaoyong Tan · 2021
Text sentiment analysis is a computer-based emotional classification of human language texts. At present, most text sentiment classification models are based on word vectors, and these models are difficult to solve the problem of polysemy. In order to effectively identify students' emotions through online comments, this paper constructs a text emotion classification model based on ALBERT and BiLSTM by using bidirectional transformers encoder. Through the contrast experiment, it is found that this model has better performance.