Weibo Disaster Rumor Recognition Method Based on Adversarial Training and Stacked Structure

다국어 초록 (Multilingual Abstract)

To solve the problems existing in the process of Weibo disaster rumor recognition, such as lack of corpus, poor text standardization, difficult to learn semantic information, and simple semantic features of disaster rumor text, this paper takes Sina Weibo as the data source, constructs a dataset for Weibo disaster rumor recognition, and proposes a deep learning model BERT_AT_Stacked LSTM for Weibo disaster rumor recognition. First, add adversarial disturbance to the embedding vector of each word to generate adversarial samples to enhance the features of rumor text, and carry out adversarial training to solve the problem that the text features of disaster rumors are relatively single. Second, the BERT part obtains the word-level semantic information of each Weibo text and generates a hidden vector containing sentence-level feature information. Finally, the hidden complex semantic information of poorly-regulated Weibo texts is learned using a Stacked Long Short-Term Memory (Stacked LSTM) structure. The experimental results show that, compared with other comparative models, the model in this paper has more advantages in recognizing disaster rumors on Weibo, with an F1_Socre of 97.48%, and has been tested on an open general domain dataset, with an F1_Score of 94.59%, indicating that the model has better generalization.

참고문헌 (Reference)

1 C. Li, "Text Similarity Computation Model for Identifying Rumor Based on Bayesian Network in Microblog" 17 (17): 731-741, 2020

2 Y. Xiong, "Set Up Scientific Procedures to Curb the Spread of Rumour of Emergencies" (07) : 16-19, 2012

3 V. Qazvinian, "Rumor has it : Identifying Misinformation in Microblogs" 1589-1599, 2011

4 T Takahashi, "Rumor detection on twitter" 2013

5 W. J. Ren, "Rumor Detection Based on Time Series Model" 09 (09): 300-303, 2019

6 X. H. Su, "Research on the Extraction of Earthquake's Hot Topic-Words form Microblog Based on Improved TF-IDF Algorithm" 34 (34): 90-95, 2018

7 Z. M. Zeng, "Research on Weibo Rumor Recognition Based on LDA and Random Forest——Taking 2016 Smog Rumors as an Example" 38 (38): 89-96, 2019

8 M. J. Gao, "Research on Weibo Rumor Recognition Based on Deep Learning" JUFE Univ 2021

9 G. He, "Research on Weibo Rumor Recognition" 57 (57): 114-120, 2013

10 R. Sun, "Research on Rumor Recognition in Public Health Emergencies" 42 (42): 8-, 2021

11 H. Li, "Research on Natural Disasters And Their Economic Costs in My Country" 004 (004): 66-72, 2010

12 X, Song, "Research on Multi-subject Rumor-refuting of Disaster Events Based on the Perspective of Collaborative Governance" ECNU Univ 2020

13 Z. C. Tian, "Research on Disaster News in Contemporary China" Fudan Univ 2005

14 L. Li, "Question Classification Method of Agricultural Diseases and Pets Based on BERT_Stacked LSTM" 52 (52): 172-177, 2021

15 H. Kyle, "Monitoring Misinformation on Twitter During Crisis Events : A Machine Learning Approach" 42 (42): 1728-1748, 2022

16 H. L. Cao, "Liminality and Rumor: A Religious Anthropological Interpretation of Earthquake Disaster" (03) : 131-135, 2010

17 R. Jang, "Japan's Great Flood in July 2018 and Its Response" 28 (28): 09-12, 2018

18 P. Agarwal, "Interplay of rumor propagation and clarification on social media during crisis events-A game-theoretic approach" 298 (298): 714-733, 2022

19 C. Castillo, "Information credibility on Twitter" 675-684, 2011

20 Z. H. Meng, "History of Famine in China" WREPP 1989

21 Z. Liu, "Early Automatic Detection of Rumors on Social Media Platforms" 005 (005): 65-80, 2018

22 A. H. Wang, "Don't Follow Me - Spam Detection in Twitter" 2010

23 J. Ma, "Detecting Rumors from Microblogs with Recurrent Neural Networks" 2016

24 Y. Lecun, "Deep Learning" 521 (521): 436-444, 2015

25 C. España-Bonet, "Automatic Speech Recognition with Deep Neural Networks for Impaired Speech" 97-107, 2016

26 F. Yang, "Automatic Detection of Rumor on Sina Weibo" 1-7, 2012

27 A. Vaswani, "Attention is All You Need" 2017

28 L. L. Ma, "An Ontology Modeling Method for Natural Disaster Events" 32 (32): 12-17, 2016

29 J. Ma, "An Attention-based Rumor Detection Model with Tree"structured Recursive Neural Networks" 11 (11): 1-28, 2020

30 T. Miyato, "Adversarial Training Methods for Semi-Supervised Text Classification" 2017

31 Z. H. Lin, "A Self-attentive Sentence Embedding" 2017

32 A. Li, "A Rumor Detection Method Based on Improved Generative Adversarial Network" 34 (34): 78-88, 2020

33 X. J. Huang, "A Real-time Detection Model of Weibo Rumors that Integrates Multi-user Features and Content Features" 1-12, 2021

34 L. Z. Li, "A Microblog Rumor Events Detection Method Based on C-GRU" 49 (49): 102-106, 2019

35 Z. Q. Wan, "1998 Flood Disaster Report" (04) : 04-, 1998