Rumour detection technology based on the BiGRU_capsule network

False information, such as rumours, has seriously affected our daily lives and threatened the political, economic, cultural and other fields. Therefore, rumour detection on social media has become a hot research topic in recent years. The development of deep learning algorithms provides new technology for rumour detection. It has been shown that capsule networks have several advantages, while their validity in the domain of text has been less explored. An effective method named the BiGRU_capsule network model has been recently proposed. This method can fully consider the contextual relationship without the loss of text spatial structure information. The proposed model introduces features of user personas and uses a two-way GRU (BiGRU) network to improve the capsule network, which can improve rumour detection accuracy. Experimental results show that compared with benchmark rumour detection models on the Twitter dataset, the accuracy of the proposed model can be improved by 6.7% under dynamic routing and by 6.1% under static routing. This reflects the effectiveness of the proposed method on rumour detection in social media.