LSTM based Online Public Opinion Rumors Recognition Method
AUTHORS
Dan Liu,Heilongjiang Vocational College of Winter Sports, Heilongjiang, China
ABSTRACT
This paper tries to judge the true and fake information of a large number of public opinions in the network, keep the truth, remove the fake, and provide reference for the government public opinion workers to judge rumors. data such as rumor and non-rumor topics, replies and other data of microblog were collected as data sets, and then programmed with paddle fluid API, and the recurrent neural network model was configured. The data set was used for model training, and finally the model analysis and detection were carried out. Through LSTM model training and data analysis, rumor events in public opinion can be digitized, and fake information feature set in text can be mined, so as to make better rumor recognition and make public opinion workers better control rumors.
KEYWORDS
Network public opinion, LSTM, Rumor recognition
REFERENCES
[1] CNNIC, “The 43rd “Statistical report on internet development in China,” http://www.cac.gov.cn/2019-02/28/c_1124175677.htm, (2019)
[2] Zhang Yuliang, “Network opinion risk evaluation index system based on the cycle of emergency,” Information Science, vol.30, no.7, pp.1034-1037, (2012)
[3] Jiang Yanchuan, Xiao Tieyan, and Ling Xiaoming, “Study on the situation of public opinions from network on campus in the new media environment and the guiding strategy,” Journal of Chongqing University (Social Science Edition), vol.18, no.1, pp.142-148, (2012)
[4] Zhao Jianhua, Wan Kewen, “Research on the communication dynamics model of social network public opinion based on the SIS model,” Information Science, vol.35, no.12, pp.34-38, (2017)
[5] Tang Tao, “Research into monitoring net-mediated public sentiment based on methods of information science”, Information Science, vol.32, no.1, pp.124-127, (2014)
[6] Xiong Yan, “Refuting and paraphrasing rumors can eliminate the illusion of fact”, Modern Communication (Journal of Communication University of China), vol.2018, no.3, pp.74-79, (2018)
[7] He Gang, Lv Xueqiang, and Li Zhuo, “Automatic rumor identification on microblog”, Library and Information Service, vol.57, no.23, pp.114-120, (2013)
[8] Liu Hanbo, “Rumors of WeChat as a risk culture - information mutual reward and role playing under “ignorance and shame”,”, National Arts, vol.2017, no.5, pp.36-41, (2017)
[9] Zhan Xin, Xia Zhijie, Luo Mengying, and He Yin, “Research on the factors affecting the collective intelligence to suppress social media rumors spreading,” Library, vol.2018, no.8, pp.85-90, (2018)
[10] Lin Rongrong, “Research on microblog rumor recognition based on sensitive word database,” Zhongnan University of Economics and Law, M.S. thesis, (2018)
[11] Jiang Ying, Zhang Jing, Zhu Lingxuan, and Qu Chang, “Analysis of online rumor text syntactical structure features and the monitoring system” Electronic Design Engineering, vol.25, no.23, pp.7-10, (2017)
[12] Deng Shengli, and Fu Shaoxiong, “An analysis of the influence of attached information on trusting and sharing health-related rumors in social media,” Information Science, vol.36, no.3, pp.51-57, (2018)
[13] Zhiwei Jin, Juan Cao, Yongdong Zhang, “News verification by exploiting conflicting social viewpoints in microblogs,” hirtieth Aaai Conference on Artificial Intelligence. AAAI Press, (2016)
[14] Chen Fan, “Research on weibo rumor recognition method based on LSTM sentiment analysis model,” Chongqing University, M.S. thesis, (2018)
[15] Yang Guiyuan, Tang Xiaowo, “A new prediction and evaluation method - loss function method,” Prediction, vol.17, no.3, pp.38-40, (1998)