Personality Classification Based on Bert Model
Jun He, Peng Liu, Changhui Jiang, Pengzheng Liu, Wu Shenke, Zhong Kejia · 2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT) · 2021
Personality classification is the process of analyzing and summarizing the relevant emotional information in the text, so as to infer the personality traits in the text. In view of the fact that traditional machine learning methods need to manually label to extract features when dealing with personality classification problems, which leads to poor per-formance of classification results. In this paper, we propose a deep learning method based on the BERT model. The model adopts the Transformer two-way coding structure, which can extract features more effectively than traditional methods. Finally, the Softmax classifier is used to classify the extracted text feature vectors. Qur experiment compares several classical models such as SVM, CNN and LSTM, and the experimental results show that the multi-classification effect of the BERT model is better than other models. It is proved that the BERT model can effectively improve the effect of personality classification.