Liang Ke
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Liang Ke has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Haizhou Wang
Sichuan University
1 shared publication - Hanjian Su
College of Cybersecurity, Sichuan University, Chengdu 610064, China
1 shared publication - Xingshu Chen
School of Cyber Science and Engineering, Sichuan University, Chengdu, China
1 shared publication - Zhipeng Lu
College of Computer Science and Technology, Zhejiang University, Hangzhou, China
1 shared publication
Latest Publications
- Open Access
- 12 October 2020
- Published by MDPI AG in Applied Sciences
- Vol. 10 (20) , 7093
A Novel Hybrid Model for Cantonese Rumor Detection on Twitter
The development of information technology and mobile Internet has spawned the prosperity of online social networks. As the world’s largest microblogging platform, Twitter is popular among people all over the world. However, as the number of users on Twitter increases, rumors have become a serious problem. Therefore, rumor detection is necessary since it can prevent unverified information from causing public panic and disrupting social order. Cantonese is a widely used language in China. However, to the best of our knowledge, little research has been done on Cantonese rumor detection. In this paper, we propose a novel hybrid model XGA (namely XLNet-based Bidirectional Gated Recurrent Unit (BiGRU) network with Attention mechanism) for Cantonese rumor detection on Twitter. Specifically, we take advantage of both semantic and sentiment features for detection. First of all, XLNet is employed to produce text-based and sentiment-based embeddings at the character level. Then we perform joint learning of character and word embeddings to obtain the words’ external contexts and internal structures. In addition, we leverage BiGRU and the attention mechanism to obtain important semantic features and use the Cantonese rumor dataset we constructed to train our proposed model. The experimental results show that the XGA model outperforms the other popular models in Cantonese rumor detection. The research in this paper provides methods and ideas for future work in Cantonese rumor detection on other social networking platforms.
- 12 October 2020
- Published by MDPI AG in Applied Sciences
- Vol. 10 (20) , 7093
Open AccessA Novel Hybrid Model for Cantonese Rumor Detection on Twitter
The development of information technology and mobile Internet has spawned the prosperity of online social networks. As the world’s largest microblogging platform, Twitter is popular among people all over the world. However, as the number of users on Twitter increases, rumors have become a serious problem. Therefore, rumor detection is necessary since it can prevent unverified information from causing public panic and disrupting social order. Cantonese is a widely used language in China. However, to the best of our knowledge, little research has been done on Cantonese rumor detection. In this paper, we propose a novel hybrid model XGA (namely XLNet-based Bidirectional Gated Recurrent Unit (BiGRU) network with Attention mechanism) for Cantonese rumor detection on Twitter. Specifically, we take advantage of both semantic and sentiment features for detection. First of all, XLNet is employed to produce text-based and sentiment-based embeddings at the character level. Then we perform joint learning of character and word embeddings to obtain the words’ external contexts and internal structures. In addition, we leverage BiGRU and the attention mechanism to obtain important semantic features and use the Cantonese rumor dataset we constructed to train our proposed model. The experimental results show that the XGA model outperforms the other popular models in Cantonese rumor detection. The research in this paper provides methods and ideas for future work in Cantonese rumor detection on other social networking platforms.