Detecting Rumors on Social Media Based on a CNN Deep Learning Technique
- PDF / 1,455,823 Bytes
- 32 Pages / 595.276 x 790.866 pts Page_size
- 63 Downloads / 232 Views
RESEARCH ARTICLE-COMPUTER ENGINEERING AND COMPUTER SCIENCE
Detecting Rumors on Social Media Based on a CNN Deep Learning Technique Abdullah Alsaeedi1
· Mohammed Al-Sarem2,3
Received: 7 January 2020 / Accepted: 29 July 2020 © King Fahd University of Petroleum & Minerals 2020
Abstract Currently, it is easy to create content and share it via social media platforms such as Twitter, Facebook, and Sina Weibo. However, some problems can occur when the shared content includes untrustworthy or misleading information. Thus, researchers from different domains have tried to investigate the impact of rumors on the global community. Several machine learning approaches have been used to detect rumors at their early stage. However, the achieved accuracies demonstrate that the existing state-of-the-art rumor detection approaches still require improvement. In this paper, we propose a deep learning model based on a conventional neural network (CNN) to detect rumors spreading on Twitter. Several experiments were conducted to find the best hyperparameter settings to improve the model’s performance. We compared our results with other relevant rumor detection approaches that used the same publicly available benchmark dataset to demonstrate our model’s performance regarding the accuracy, precision, recall and f -measure. The results show that our CNN model outperforms all the existing approaches and achieves the best balance of recall and precision. Keywords Rumor detection · Deep learning · Twitter analysis · Convolution deep learning · Hyperparameters settings · PHEME dataset
1 Introduction With the development of online social networking (OSN) services, people can easily create their content and share it with the public. Social media platforms such as Twitter, Facebook, and Sina Weibo, have become a major source of information and play a vital role in informing the public of various events. However, despite these advantages, OSN services have become a breeding ground for several kinds of misinformation, especially rumors that can affect the readers’ opinions and the accuracy of the information being carried out as a result of such news [1]. Researchers from different
B
Abdullah Alsaeedi [email protected] Mohammed Al-Sarem [email protected]
1
Computer Science Department, College of Computer Science and Engineering, Taibah University, Medina, Saudi Arabia
2
Information System Department, College of Computer Science and Engineering, Taibah University, Medina, Saudi Arabia
3
Information System Department, Saba’a Region Universitry, Mareeb, Yemen
scientific fields have shown interest in detecting rumors at their early stages to overcome the harm that rumors might cause for the public. In general, most of the current methods treat rumor detection as a binary classification problem where the content (defused information via OSN) is classified as rumor or non-rumor [2,3]. Currently, the research interests around rumor detection are focused on applying either traditional machine learning methods [2,4–6] or deep learning met
Data Loading...
