Emotion Analysis Based on Deep Learning With Application to Research on Development of Western Culture
Cultural development is often reflected in the emotional expression of various cultural carriers, such as literary works, movies, etc. Therefore, the cultural development can be analyzed through emotion analysis of the text, so as to sort out its context and obtain its development dynamics. This pap...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-09-01
|
| Series: | Frontiers in Psychology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyg.2022.911686/full |
| _version_ | 1818055875518005248 |
|---|---|
| author | Ming Chen |
| author_facet | Ming Chen |
| author_sort | Ming Chen |
| collection | DOAJ |
| description | Cultural development is often reflected in the emotional expression of various cultural carriers, such as literary works, movies, etc. Therefore, the cultural development can be analyzed through emotion analysis of the text, so as to sort out its context and obtain its development dynamics. This paper proposes a text emotion analysis method based on deep learning. The traditional neural network model mainly deals with the classification task of short texts in the form of word vectors, which causes the model to rely too much on the accuracy of word segmentation. In addition, the short texts have the characteristics of short corpus and divergent features. A text emotion classification model combing the Bidirectional Encoder Representations from Transformers (BERT) and Bi-directional Long Short-Term Memory (BiLSTM) is developed in this work. First, the BERT model is used to convert the trained text into a word-based vector representation. Then, the generated word vector is employed as the input of the BiLSTM to obtain the semantic representation of the context of the relevant word. By adding random dropout, the mechanism prevents the model from overfitting. Finally, the extracted feature vector is input to the fully connected layer, and the emotion category to which the text belongs is calculated through the Softmax function. Experiments show that in processing short texts, the proposed model based on BERT-BiLSTM is more accurate and reliable than the traditional neural network model using word vectors. The proposed method has a better analysis effect on the development of western culture. |
| first_indexed | 2024-12-10T12:19:54Z |
| format | Article |
| id | doaj.art-ed4ac00ef737470d85c5dfb0c4ed5b01 |
| institution | Directory Open Access Journal |
| issn | 1664-1078 |
| language | English |
| last_indexed | 2024-12-10T12:19:54Z |
| publishDate | 2022-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychology |
| spelling | doaj.art-ed4ac00ef737470d85c5dfb0c4ed5b012022-12-22T01:49:07ZengFrontiers Media S.A.Frontiers in Psychology1664-10782022-09-011310.3389/fpsyg.2022.911686911686Emotion Analysis Based on Deep Learning With Application to Research on Development of Western CultureMing ChenCultural development is often reflected in the emotional expression of various cultural carriers, such as literary works, movies, etc. Therefore, the cultural development can be analyzed through emotion analysis of the text, so as to sort out its context and obtain its development dynamics. This paper proposes a text emotion analysis method based on deep learning. The traditional neural network model mainly deals with the classification task of short texts in the form of word vectors, which causes the model to rely too much on the accuracy of word segmentation. In addition, the short texts have the characteristics of short corpus and divergent features. A text emotion classification model combing the Bidirectional Encoder Representations from Transformers (BERT) and Bi-directional Long Short-Term Memory (BiLSTM) is developed in this work. First, the BERT model is used to convert the trained text into a word-based vector representation. Then, the generated word vector is employed as the input of the BiLSTM to obtain the semantic representation of the context of the relevant word. By adding random dropout, the mechanism prevents the model from overfitting. Finally, the extracted feature vector is input to the fully connected layer, and the emotion category to which the text belongs is calculated through the Softmax function. Experiments show that in processing short texts, the proposed model based on BERT-BiLSTM is more accurate and reliable than the traditional neural network model using word vectors. The proposed method has a better analysis effect on the development of western culture.https://www.frontiersin.org/articles/10.3389/fpsyg.2022.911686/fulldeep learningemotion analysisBERTBiLSTMcultural development |
| spellingShingle | Ming Chen Emotion Analysis Based on Deep Learning With Application to Research on Development of Western Culture Frontiers in Psychology deep learning emotion analysis BERT BiLSTM cultural development |
| title | Emotion Analysis Based on Deep Learning With Application to Research on Development of Western Culture |
| title_full | Emotion Analysis Based on Deep Learning With Application to Research on Development of Western Culture |
| title_fullStr | Emotion Analysis Based on Deep Learning With Application to Research on Development of Western Culture |
| title_full_unstemmed | Emotion Analysis Based on Deep Learning With Application to Research on Development of Western Culture |
| title_short | Emotion Analysis Based on Deep Learning With Application to Research on Development of Western Culture |
| title_sort | emotion analysis based on deep learning with application to research on development of western culture |
| topic | deep learning emotion analysis BERT BiLSTM cultural development |
| url | https://www.frontiersin.org/articles/10.3389/fpsyg.2022.911686/full |
| work_keys_str_mv | AT mingchen emotionanalysisbasedondeeplearningwithapplicationtoresearchondevelopmentofwesternculture |