An Effective Personality-Based Model for Short Text Sentiment Classification Using BiLSTM and Self-Attention
While user-generated textual content on social platforms such as Weibo provides valuable insights into public opinion and social trends, the influence of personality on sentiment expression has been largely overlooked in previous studies, especially in Chinese short texts. To bridge this gap, we pro...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/15/3274 |
| _version_ | 1797586851269181440 |
|---|---|
| author | Kejian Liu Yuanyuan Feng Liying Zhang Rongju Wang Wei Wang Xianzhi Yuan Xuran Cui Xianyong Li Hailing Li |
| author_facet | Kejian Liu Yuanyuan Feng Liying Zhang Rongju Wang Wei Wang Xianzhi Yuan Xuran Cui Xianyong Li Hailing Li |
| author_sort | Kejian Liu |
| collection | DOAJ |
| description | While user-generated textual content on social platforms such as Weibo provides valuable insights into public opinion and social trends, the influence of personality on sentiment expression has been largely overlooked in previous studies, especially in Chinese short texts. To bridge this gap, we propose the P-BiLSTM-SA model, which integrates personalities into sentiment classification by combining BiLSTM and self-attention mechanisms. We grouped Weibo texts based on personalities and constructed a personality lexicon using the Big Five theory and clustering algorithms. Separate sentiment classifiers were trained for each personality group using BiLSTM and self-attention, and their predictions were combined by ensemble learning. The performance of the P-BiLSTM-SA model was evaluated on the NLPCC2013 dataset and showed significant accuracy improvements. In particular, it achieved 82.88% accuracy on the NLPCC2013 dataset, a 7.51% improvement over the baseline BiLSTM-SA model. The results highlight the effectiveness of incorporating personality factors into sentiment classification of short texts. |
| first_indexed | 2024-03-11T00:29:00Z |
| format | Article |
| id | doaj.art-0503964d5840415cb6cb51864d73a9f1 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T00:29:00Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-0503964d5840415cb6cb51864d73a9f12023-11-18T22:48:49ZengMDPI AGElectronics2079-92922023-07-011215327410.3390/electronics12153274An Effective Personality-Based Model for Short Text Sentiment Classification Using BiLSTM and Self-AttentionKejian Liu0Yuanyuan Feng1Liying Zhang2Rongju Wang3Wei Wang4Xianzhi Yuan5Xuran Cui6Xianyong Li7Hailing Li8School of Computer and Software Engineering, Xihua University, Chengdu 610039, ChinaState Grid Suining Power Supply Company, Suining 629000, ChinaSchool of Computer and Software Engineering, Xihua University, Chengdu 610039, ChinaSchool of Computer and Software Engineering, Xihua University, Chengdu 610039, ChinaSchool of Computer and Software Engineering, Xihua University, Chengdu 610039, ChinaSchool of Computer and Software Engineering, Xihua University, Chengdu 610039, ChinaSchool of Computer and Software Engineering, Xihua University, Chengdu 610039, ChinaSchool of Computer and Software Engineering, Xihua University, Chengdu 610039, ChinaSchool of Architecture and Civil Engineering, Xihua University, Chengdu 610039, ChinaWhile user-generated textual content on social platforms such as Weibo provides valuable insights into public opinion and social trends, the influence of personality on sentiment expression has been largely overlooked in previous studies, especially in Chinese short texts. To bridge this gap, we propose the P-BiLSTM-SA model, which integrates personalities into sentiment classification by combining BiLSTM and self-attention mechanisms. We grouped Weibo texts based on personalities and constructed a personality lexicon using the Big Five theory and clustering algorithms. Separate sentiment classifiers were trained for each personality group using BiLSTM and self-attention, and their predictions were combined by ensemble learning. The performance of the P-BiLSTM-SA model was evaluated on the NLPCC2013 dataset and showed significant accuracy improvements. In particular, it achieved 82.88% accuracy on the NLPCC2013 dataset, a 7.51% improvement over the baseline BiLSTM-SA model. The results highlight the effectiveness of incorporating personality factors into sentiment classification of short texts.https://www.mdpi.com/2079-9292/12/15/3274deep learningpersonality recognitionsentiment classificationBiLSTMself-attentionbig five |
| spellingShingle | Kejian Liu Yuanyuan Feng Liying Zhang Rongju Wang Wei Wang Xianzhi Yuan Xuran Cui Xianyong Li Hailing Li An Effective Personality-Based Model for Short Text Sentiment Classification Using BiLSTM and Self-Attention Electronics deep learning personality recognition sentiment classification BiLSTM self-attention big five |
| title | An Effective Personality-Based Model for Short Text Sentiment Classification Using BiLSTM and Self-Attention |
| title_full | An Effective Personality-Based Model for Short Text Sentiment Classification Using BiLSTM and Self-Attention |
| title_fullStr | An Effective Personality-Based Model for Short Text Sentiment Classification Using BiLSTM and Self-Attention |
| title_full_unstemmed | An Effective Personality-Based Model for Short Text Sentiment Classification Using BiLSTM and Self-Attention |
| title_short | An Effective Personality-Based Model for Short Text Sentiment Classification Using BiLSTM and Self-Attention |
| title_sort | effective personality based model for short text sentiment classification using bilstm and self attention |
| topic | deep learning personality recognition sentiment classification BiLSTM self-attention big five |
| url | https://www.mdpi.com/2079-9292/12/15/3274 |
| work_keys_str_mv | AT kejianliu aneffectivepersonalitybasedmodelforshorttextsentimentclassificationusingbilstmandselfattention AT yuanyuanfeng aneffectivepersonalitybasedmodelforshorttextsentimentclassificationusingbilstmandselfattention AT liyingzhang aneffectivepersonalitybasedmodelforshorttextsentimentclassificationusingbilstmandselfattention AT rongjuwang aneffectivepersonalitybasedmodelforshorttextsentimentclassificationusingbilstmandselfattention AT weiwang aneffectivepersonalitybasedmodelforshorttextsentimentclassificationusingbilstmandselfattention AT xianzhiyuan aneffectivepersonalitybasedmodelforshorttextsentimentclassificationusingbilstmandselfattention AT xurancui aneffectivepersonalitybasedmodelforshorttextsentimentclassificationusingbilstmandselfattention AT xianyongli aneffectivepersonalitybasedmodelforshorttextsentimentclassificationusingbilstmandselfattention AT hailingli aneffectivepersonalitybasedmodelforshorttextsentimentclassificationusingbilstmandselfattention AT kejianliu effectivepersonalitybasedmodelforshorttextsentimentclassificationusingbilstmandselfattention AT yuanyuanfeng effectivepersonalitybasedmodelforshorttextsentimentclassificationusingbilstmandselfattention AT liyingzhang effectivepersonalitybasedmodelforshorttextsentimentclassificationusingbilstmandselfattention AT rongjuwang effectivepersonalitybasedmodelforshorttextsentimentclassificationusingbilstmandselfattention AT weiwang effectivepersonalitybasedmodelforshorttextsentimentclassificationusingbilstmandselfattention AT xianzhiyuan effectivepersonalitybasedmodelforshorttextsentimentclassificationusingbilstmandselfattention AT xurancui effectivepersonalitybasedmodelforshorttextsentimentclassificationusingbilstmandselfattention AT xianyongli effectivepersonalitybasedmodelforshorttextsentimentclassificationusingbilstmandselfattention AT hailingli effectivepersonalitybasedmodelforshorttextsentimentclassificationusingbilstmandselfattention |