ABSTRACT
With the rapid development of network and social media, the operation and maintenance department of power supply enterprises is facing a complex situation of network public opinion. How to use deep learning method to analyze the public opinion information of power operation and maintenance is a topic worthy of our consideration. In view of the high cost of manual annotation of public opinion training in the field of power operation and maintenance, and combined with the characteristics of public opinion analysis in the field of power operation and maintenance, this paper adopts the active learning strategy and the dual channel convolution neural network (WEP-CNN) model which integrates the emotional polarity of words to analyze public opinion. The model greatly improves the labeling efficiency of data sets, and achieves significant improvement in accuracy, recall, F1 value and other indicators.
- Xin Wang. Innovative Practice of Maintaining State Grid Brand under the New Ecology of Public Opinion. Low Carbon World, 2017(27): 108-109.Google Scholar
- Yang Guoliang. Establishing modern communication concept and improving public opinion guiding ability. China Electric Power, 2012(1): 72-73.Google Scholar
- Yu Guoming, editor-in-chief. Annual Report on Public Opinion in China 2010[M]. Beijing: People's Daily Press, 2010:274.Google Scholar
- Wang Guohua, Feng Wei, Wang Yalei. Research on Coping with Internet Public Opinion Based on Classification [J]. Journal of information, 2013, 32(5): 1-4. Google Scholar
- Wang Gaofei, Li Runzhi, Li Mei. A Summary of Research on Internet Public Opinion in Weibo. Today Media, 2021, 29(1): 24-29.Google Scholar
- Wang Gaofei, Pei Jingzhao, Song Zhuangzhuang. A Review of Research on Emotional Analysis of Internet Public Opinion. Cooperative Economy and Technology, 2021(2): 176-178.Google Scholar
- Ma Zhicheng, gu kaicheng, Yang Peng. Design and implementation of public opinion recognition scheme for power enterprises based on text classification [J]. Electronic design engineering, 2017, 0(3): 28-31.Google Scholar
- Zeng Jiani, Liu Gongshen, Su Bo. Research on Emotional Analysis of Weibo's Topic Comments [J]. Information Security and Communication Secrecy, 2013(3).Google Scholar
- Zhu Le, Li Qiuping, Zhu Yidan. Analysis of Internet Public Opinion of "Educational Equity" Based on Deep Learning. Information Exploration, 2020(6): 40-47.Google Scholar
- Yu zhang. Research on Network Public Opinion Analysis Method Based on Multiple Convolution Cycle. Electronic Design Engineering, 2020,28(18):92-96.Google Scholar
- Zhao Yiming, Xie Jiong, Chen Xiaoyu, Ren Ren, Du Dong, Li Qi, Li Ying. Design and implementation of power public opinion butler system based on big data. Power Information and Communication Technology, 2019, 17(8): 31-36.Google Scholar
- Han Yaoting, Zhao Yiming, Xie Jiong, Chen Xiaoyu, Yang Huyun. Research on Cloud Platform of Network Public Opinion Discovery in Electric Power Enterprises under Emergency. Electric Power Information and Communication Technology, 2019, 17(11): 70-75.Google Scholar
- Kim, Yoon. Convolutional Neural Networks for Sentence Classification [J]. Eprint Arxiv, 2014.Google Scholar
- Xu Lulei. Comparison of the methods of obtaining emotional words and judging polarity in online reviews. Computer and Telecommunications, 2011(1): 53-55.Google Scholar
- Joulin A, Grave E , Bojanowski P, Bag of Tricks for Efficient Text Classification[J]. 2016Google Scholar
- Lai S, Xu L, Liu K, Recurrent Convolutional Neural Networks for Text Classification. 2015.Google ScholarCross Ref
Recommendations
Identifying Opinion Sentences and Opinion Holders in Internet Public Opinion
ICICEE '12: Proceedings of the 2012 International Conference on Industrial Control and Electronics EngineeringIn this paper, we propose to automatic identify opinion sentences and opinion holders in Internet Public Opinion. We established a series of related resources to opinion analysis, such as opinion operator set etc. Based on these related resources, we ...
Research of Several Key Issues of the Internet Public Opinion in China
MISNC '17: Proceedings of the 4th Multidisciplinary International Social Networks ConferenceWith the development of the Internet, the Internet public opinion has become one of the hot issues of public opinion research. While bringing convenience to the society, the Internet development may also trigger the corresponding contradictions and ...
Comments