التفاصيل البيبلوغرافية
| العنوان: |
An exploratory study of deep learning-based sentiment analysis among Weibo users in China. |
| المؤلفون: |
Song, Jian1 (AUTHOR), Wang, Mengmeng1 (AUTHOR), Li, Yingwu1 (AUTHOR) liyingwu@ruc.edu.cn |
| المصدر: |
Current Psychology. May2024, Vol. 43 Issue 17, p15213-15226. 14p. |
| مصطلحات موضوعية: |
*SENTIMENT analysis, SOCIAL media, SELF-expression, EMOTION recognition, DEEP learning |
| مصطلحات جغرافية: |
SHIJIAZHUANG (Hebei Sheng, China), CHINA |
| مستخلص: |
Adjustments to COVID-19 prevention and control strategies were closely linked to individuals and elicited psychological and behavioral responses within the public. To investigate public emotions in Shijiazhuang from November 13 to November 23, 2022, we utilized web crawler technology, Ekman's six basic emotion model, and the fine-tuned BERT deep learning model for sentiment analysis on Weibo, China's largest social media platform. The results indicated that: (i) spatially, the adjustment of the epidemic prevention strategy, despite its significance as a major public event, did not produce a significant emotional ripple effect; (ii) temporally, public emotions displayed substantial fluctuations as the event unfolded, marked by swift reaction times, demonstrating a typical temporal pattern; (iii) when comparing trends in the six emotion indices, a consistent pattern of public emotional expression on social media emerged. The deep learning BERT technology utilized in this study achieved an emotion recognition accuracy rate of 88.50% when applied to a large dataset of social media text. This study provides theoretical foundations and novel insights for conducting sentiment analysis of significant public events through the analysis of social media data. [ABSTRACT FROM AUTHOR] |
|
Copyright of Current Psychology is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| قاعدة البيانات: |
Business Source Index |
