Adaptive gate residual connection and multi-scale RCNN for fake news detection

Abstract

Detection of false news based on text classification technology has significant research significance and practical value in the current information age. However, existing methods overlook the problem of uneven sample distribution in the false news dataset and fail to consider the mutual influence between news articles. In light of this, this paper proposes a new method for false news detection. Firstly, news texts are embedded using Electra (Efficiently Learning an Encoder that Classifies Token Replacements Accurately) to obtain word embedding representations. Secondly, Multi-Scale Recurrent Convolutional Neural Network (RCNN) is employed to further extract contextual information from news texts. Self-attention is introduced to calculate attention scores between news articles, allowing for mutual influence between news features. The establishment of connections between modules is achieved through adaptive gated residual connections. Finally, the focal loss function is used to balance the relationship between few-sample and multi-sample data in the dataset. Experimental results on publicly available false news detection datasets demonstrate that the proposed method achieves higher prediction accuracy than the comparative methods. This method provides a new perspective for the field of false news detection, playing a positive role in promoting information authenticity and protecting public interests.