基于深度学习的网络舆情监测系统研究

doi:10.16180/j.cnki.issn1007-7820.2022.12.014

电子科技 ›› 2022, Vol. 35 ›› Issue (12): 97-102.doi: 10.16180/j.cnki.issn1007-7820.2022.12.014

• • 上一篇

基于深度学习的网络舆情监测系统研究

邓磊¹,孙培洋²

1.西北政法大学新闻传播学院, 陕西西安 710000
2.西安理工大学自动化与信息工程学院,陕西西安 710000

收稿日期:2021-06-30 出版日期:2022-12-15 发布日期:2022-12-13
作者简介:邓磊(1976-),男,博士,讲师。研究方向:自然语言处理、大数据网络舆情分析与研判。|孙培洋(2001-),女,本科。研究方向:电子信息与软件工程、自然语言处理。
基金资助:
西安市科学技术局软bepaly手机下载项目(2021RKYJ0016);国家社会科学基金项目(18XXW006)

Research on Network Public Opinion Monitoring System Based on Deep Learning

DENG Lei¹,SUN Peiyang²

1. School of Journalism and Communication, Northwest University of Political Science and Law, Xi'an 710000,China
2. School of Automation and Information Engineering, Xi'an University of Technology, Xi'an 710000,China

Received:2021-06-30 Online:2022-12-15 Published:2022-12-13
Supported by:
Soft Science Research Project of Xi'an Science and Technology Bureau(2021RKYJ0016);National Social Science Foundation of China(18XXW006)

摘要/Abstract

摘要：

随着国内互联网的快速发展,网络舆情监测工作已经成为相关部门、企业工作内容的一部分。构建舆情监测系统可以提前发现舆情危机,及时处理危机公关。文中提出了一个完整的网络舆情监测系统框架,该系统由信息采集层、数据资源层、数据分析应用层和应用服务层4部分组成。该系统首先根据关键词自动采集全网多数门户网站、微博和微信公众号中的数据,包括文章与评论;然后将这些数据进行清洗、分词并过滤停用词,利用Word2Vec模型进行词嵌入,得到矢量化文本;随后再将矢量化的文本导入LSTM深度学习模型中进行情感分析,进一步将数据分为敏感数据、中性数据和非敏感数据;最后将舆情预警信息通过可视化技术显示。文中所提出的网络舆情监测系统可以帮助监管部门及时监测和引导相关舆论,促进社会和谐发展。

关键词: 网络舆情, 舆情监测, 情感分析, 数据分析, 深度学习, 主题检测与跟踪, 卷积神经网络, 长短期记忆网络

Abstract:

With the rapid development of the domestic Internet, network public opinion monitoring has become a part of the work of relevant departments and enterprises. Establishment of a public opinion monitoring system can detect public opinion crises in advance and deal with crisis public relations in time. The current study presents a complete framework of network public opinion monitoring system, which consists of four parts: information collection layer, data resource layer, data analysis application layer and application service layer. First, the proposed system can automatically collect data from most portals, microblogs and WeChat accounts, including articles and comments according to keywords. Then, these data are cleaned, segmented and filtered, and the word is embedded using Word2Vec model to obtain the vectorized text. The vectorized text is imported into LSTM deep learning model for sentiment analysis, and the data can be divided into sensitive data, neutral data and non-sensitive data. Finally, the public opinion warning information is displayed by visualization technology. The proposed network public opinion monitoring system can help regulators to monitor and guide relevant public opinions in a timely manner, and promote the harmonious development of society.

Key words: network public opinion, public opinion monitoring, sentiment analysis, data analysis, deep learning, topic detection and tracking, convolutional neural network, long short-term memory

中图分类号:

TP391.1

邓磊,孙培洋. 基于深度学习的网络舆情监测系统研究[J]. 电子科技, 2022, 35(12): 97-102.

DENG Lei,SUN Peiyang. Research on Network Public Opinion Monitoring System Based on Deep Learning[J]. Electronic Science and Technology, 2022, 35(12): 97-102.

图/表 11

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

参考文献 18

[1]	中国互联网络信息中心. 第49次《中国互联网络发展状况统计报告》[J]. 新闻潮, 2022, 1(2):1-2.
	CNNIC. The forty-ninth statistical report on the devel-opment of Internet in China[J]. Journalism Tide, 2022, 1(2):1-2.
[2]	Wang X, Wei Y, Xing Y, et al. Research on the dynamics and trends of the development of public opinion topic maps in social networks[J]. Journal of the China Society for Scientific and Technical Information, 2019, 38(12):1329-1338.
[3]	张航, 张欣, 张平康. 基于Hadoop的精准扶贫大数据信息系统[J]. 电子科技, 2018, 31(7):59-62,71.
	Zhang Hang, Zhang Xin, Zhang Pingkang. Big data info-rmation system for targeted poverty alleviation based on Hadoop[J]. Electronic Science and Technology, 2018, 31(7):59-62,71.
[4]	Liu D, Zhang H, Yu H, et al. Research on network publicopinion analysis and monitor method based on big data technology[C]. Beijing: IEEE the Tenth International Conference on Electronics Information and Emergency Communication, 2020.
[5]	Pan Y, Liang M. Chinese text sentiment analysis based on BI-GRU and self-attention[C]. Chongqing: IEEE the Fourth Information Technology,Networking,Electronic and Automation Control Conference, 2020.
[6]	Mao S B, Rajan D, Chia L T. Deep residual pooling net-work for texture recognition[J]. Pattern Recognition, 2021, 112(4):107817-107825. doi: 10.1016/j.patcog.2021.107817
[7]	Vamshi K B, Pandey A K, Siva KA P. Topic model based opinion mining and sentiment analysis[C]. Coimbatore: International Conference on Computer Communication and Informatics, 2018.
[8]	Wei W, Xiang Y, Chen Q. Survey on Chinese text senti-ment analysis[J]. Journal of Computer Applications, 2011, 31(12):3321-3323.
[9]	Anbukkarasi S, Varadhaganapathy S. Analyzing sentiment in tamil tweets using deep neural network[C]. Erode: The Fourth International Conference on Computing Methodologies and Communication, 2020.
[10]	Li M, Lu Q, Long Y, et al. Inferring affective meanings of words from word embedding[J]. IEEE Transactions on Affective Computing, 2017, 8(4):443-456. doi: 10.1109/TAFFC.2017.2723012
[11]	Rueden L V, Mayer S, Beckh K, et al. Informed machine learning-A taxonomy and survey of integrating prior knowledge into learning systems[J]. IEEE Transactions on Knowledge and Data Engineering, 2021, 33(5):1-7.
[12]	Liu G, Guo J B. Bidirectional LSTM with attention mechanism and convolutional layer for text classification[J]. Neurocomputing, 2019, 337(4):325-338. doi: 10.1016/j.neucom.2019.01.078
[13]	Prabowo Y D, Warnars H L H S, Budiharto W, et al. Lstm and simple Rnn comparison in the problem of sequence to sequence on conversation data using bahasaindonesia[C]. Tangerang: Indonesian Association for Pattern Recognition International Conference, 2018.
[14]	Xiao J, Zhou Z. Research progress of RNN language model[C]. Dalian: IEEE International Conference on Artificial Intelligence and Computer Applications, 2020.
[15]	葛靖, 刘子龙. 基于CNN和LSTM的睡眠呼吸暂停检测算法[J]. 电子科技, 2021, 34(2):21-26.
	Ge Jing, Liu Zilong. The algorithm based on CNN and LSTM for sleep apnea syndrome detection[J]. Electronic Science and Technology, 2021, 34(2):21-26.
[16]	Araque O, Corcuera-Platas I, Sanchez-Rada J F, et al. En-hancing deep learning sentiment analysis with ensemble techniques in social applications[J]. Expert Systems with Applications, 2017, 77(7):236-246. doi: 10.1016/j.eswa.2017.02.002
[17]	Li G, Zheng Q, Zhang L, et al. Sentiment infomation based model for Chinese text sentiment analysis[C]. Shenyang: IEEE the Third International Conference on Automation,Electronics and Electrical Engineering, 2020.
[18]	Niu G, Zhu F, Chen Z, et al. Efficient visualization system construction using common data model[C]. Weihai: IEEE the Second International Conference on Civil Aviation Safety and Information Technology, 2020.

基于深度学习的网络舆情监测系统研究

Research on Network Public Opinion Monitoring System Based on Deep Learning

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 18

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	毕嘉桢,沈拓,张轩雄. 基于机器视觉的轨道交通自动测距研究[J]. 电子科技, 2022, 35(9): 37-43.
[2]	邓源,施一萍,江悦莹,朱亚梅,刘瑾. 基于MobileNetV2与LBP特征融合的婴幼儿表情识别算法[J]. 电子科技, 2022, 35(8): 47-52.
[3]	张乔木,钟倩文,孙明,罗文成,柴晓冬. 复杂环境下弓网接触位置动态监测方法研究[J]. 电子科技, 2022, 35(8): 66-72.
[4]	赵轩,周凡,余汉成. 基于改进特征提取及融合模块的YOLOv3模型[J]. 电子科技, 2022, 35(7): 40-45.
[5]	孙抗,轩旭阳,刘鹏辉,赵来军,龙洁. 小样本下基于CNN-DCGAN的电缆局部放电模式识别方法[J]. 电子科技, 2022, 35(7): 7-13.
[6]	孔凡书,齐金鹏,龚汉鑫,朱俊俊,曹一彤. 一种基于波动向量分级技术的病变数据快速分析方法[J]. 电子科技, 2022, 35(7): 1-6.
[7]	龚汉鑫,齐金鹏,孔凡书,朱俊俊,曹一彤. 一种基于模板匹配与隶属度解析的时序异常快速检测方法[J]. 电子科技, 2022, 35(6): 1-5.
[8]	沈宁静,袁健. 基于残差密集连接与注意力融合的人群计数算法[J]. 电子科技, 2022, 35(6): 6-12.
[9]	林潮威,李菲菲,陈虬. 基于深度卷积特征的场景全局与局部表示方法[J]. 电子科技, 2022, 35(4): 20-27.
[10]	纪玲玉,高永彬,赵呈陆,汤先华,徐凯成,徐嘉诚. 基于3D全卷积网络的腹部动脉CTA分割算法[J]. 电子科技, 2022, 35(3): 38-44.
[11]	陈鹏,刘子龙. 基于GAN-CNN的心律失常识别[J]. 电子科技, 2022, 35(3): 45-50.
[12]	李辉,王一丞. 基于CNNCIFG-Attention模型的文本情感分类[J]. 电子科技, 2022, 35(2): 46-51.
[13]	朱俊俊,齐金鹏,钟金美,任晴,曹一彤. 一种基于随机交叠策略的多突变点在线检测方法[J]. 电子科技, 2022, 35(12): 1-9.
[14]	王夏霖,阚秀,范艺璇. 基于LSTM-Attention的P300事件相关电位识别分类研究[J]. 电子科技, 2022, 35(12): 10-16.
[15]	于润润,姜晓燕,朱凯赢,蒋光好. 基于上下文注意力机制的实时语义分割[J]. 电子科技, 2022, 35(12): 57-63.