An emotional classification method of Chinese short comment text based on ELECTRA
Chinese short comment texts have the characteristics of feature sparseness, interlacing, irregularity, etc., which makes it difficult to fully grasp the overall emotional tendency of users. In response to such problem, the text proposes a new method based on ELECTRA and hybrid neural network. This m...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2022-12-01
|
| Series: | Connection Science |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/09540091.2021.1985968 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849699838312054784 |
|---|---|
| author | Shunxiang Zhang Hongbin Yu Guangli Zhu |
| author_facet | Shunxiang Zhang Hongbin Yu Guangli Zhu |
| author_sort | Shunxiang Zhang |
| collection | DOAJ |
| description | Chinese short comment texts have the characteristics of feature sparseness, interlacing, irregularity, etc., which makes it difficult to fully grasp the overall emotional tendency of users. In response to such problem, the text proposes a new method based on ELECTRA and hybrid neural network. This method can more accurately capture the emotional features of the text, improve the classification effect, enhance the evaluation feedback mechanism, and facilitate user decision-making. First, in the embedding layer, ELECTRA model is used to replace BERT model, which can avoid the inconsistency of the mask training and fine-tuning process of the traditional pre-training model. Then, in the training layer, the self-attention mechanism and the BiLSTM are selected to obtain the fine-grained semantic representation information of the review text more comprehensively. Finally, in the output layer, the softmax classifier classifies the input corpus according to the sentiment characteristics of the Chinese short text. The experimental results show that the proposed model has an efficiently improvement in accuracy and there are some discoveries about the training effect of the pre-training model on text sentiment analysis tasks. |
| format | Article |
| id | doaj-art-2e105975a54c42a89ead3eaeec72ce81 |
| institution | DOAJ |
| issn | 0954-0091 1360-0494 |
| language | English |
| publishDate | 2022-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Connection Science |
| spelling | doaj-art-2e105975a54c42a89ead3eaeec72ce812025-08-20T03:18:27ZengTaylor & Francis GroupConnection Science0954-00911360-04942022-12-0134125427310.1080/09540091.2021.19859681985968An emotional classification method of Chinese short comment text based on ELECTRAShunxiang Zhang0Hongbin Yu1Guangli Zhu2Anhui University of Science & TechnologyAnhui University of Science & TechnologyAnhui University of Science & TechnologyChinese short comment texts have the characteristics of feature sparseness, interlacing, irregularity, etc., which makes it difficult to fully grasp the overall emotional tendency of users. In response to such problem, the text proposes a new method based on ELECTRA and hybrid neural network. This method can more accurately capture the emotional features of the text, improve the classification effect, enhance the evaluation feedback mechanism, and facilitate user decision-making. First, in the embedding layer, ELECTRA model is used to replace BERT model, which can avoid the inconsistency of the mask training and fine-tuning process of the traditional pre-training model. Then, in the training layer, the self-attention mechanism and the BiLSTM are selected to obtain the fine-grained semantic representation information of the review text more comprehensively. Finally, in the output layer, the softmax classifier classifies the input corpus according to the sentiment characteristics of the Chinese short text. The experimental results show that the proposed model has an efficiently improvement in accuracy and there are some discoveries about the training effect of the pre-training model on text sentiment analysis tasks.http://dx.doi.org/10.1080/09540091.2021.1985968electra pre-trained modeltext sentiment classificationattention mechanismbilstm |
| spellingShingle | Shunxiang Zhang Hongbin Yu Guangli Zhu An emotional classification method of Chinese short comment text based on ELECTRA Connection Science electra pre-trained model text sentiment classification attention mechanism bilstm |
| title | An emotional classification method of Chinese short comment text based on ELECTRA |
| title_full | An emotional classification method of Chinese short comment text based on ELECTRA |
| title_fullStr | An emotional classification method of Chinese short comment text based on ELECTRA |
| title_full_unstemmed | An emotional classification method of Chinese short comment text based on ELECTRA |
| title_short | An emotional classification method of Chinese short comment text based on ELECTRA |
| title_sort | emotional classification method of chinese short comment text based on electra |
| topic | electra pre-trained model text sentiment classification attention mechanism bilstm |
| url | http://dx.doi.org/10.1080/09540091.2021.1985968 |
| work_keys_str_mv | AT shunxiangzhang anemotionalclassificationmethodofchineseshortcommenttextbasedonelectra AT hongbinyu anemotionalclassificationmethodofchineseshortcommenttextbasedonelectra AT guanglizhu anemotionalclassificationmethodofchineseshortcommenttextbasedonelectra AT shunxiangzhang emotionalclassificationmethodofchineseshortcommenttextbasedonelectra AT hongbinyu emotionalclassificationmethodofchineseshortcommenttextbasedonelectra AT guanglizhu emotionalclassificationmethodofchineseshortcommenttextbasedonelectra |