A Stochastic Attention CNN Model for Rumor Stance Classification

Na Bai,Zhixiao Wang,Fanrong Meng

doi:10.1109/access.2020.2990770

Abstract

Rumor stance classification is a task for identifying different stances about specific social media posts, and it is considered as an important step to prevent rumors from spreading. However, most previous studies for the rumor stance classification, which focus on content features of posts, ignore the textual information granularity and reading (or writing) habits of the public. In social networks, people may have different stances towards unverified posts with different reading habits. Based on this observation, we propose a Stochastic Attention Convolutional Neural Net (SACNN) under different textual information granularity to catch different habits of the public for the rumor stance classification task. Specifically, being treated as view-windows of readers, convolutional kernels in a SACNN contain trainable convolutional kernels and stochastic untrainable convolutional kernels, and different sizes of the stochastic convolutional kernels are used to simulate casual online reading habits and to extract course-grained features such as phrase features. After the convolutional layer, fine-grained features such as keywords can be extracted by a pooling layer. The experiments show that the average accuracy and F1 score of our proposed model are respectively 0.26% and 0.46% higher than the state-of-the-art results on the rumor stance classification task on PHEME dataset.

Highlights

The popularity of social network makes rumors spread quickly, and the unverified rumors may cause anxiety and panic [1], [2]
Based on the above observations, we propose a Stochastic Attention Convolutional Neural Net (SACNN), which contains a Convolutional Neural Networks (CNNs) model and a stochastic attention mechanism
In order to simulate this reading habits, we introduce the idea of stochastic attention to convolutional and pooling layers, and the convolutional kernels are divided into two parts, one of them are untrainable kernels which are initialized randomly, the other of them are trained using conventional BP algorithm

Summary

INTRODUCTION

The popularity of social network makes rumors spread quickly, and the unverified rumors may cause anxiety and panic [1], [2]. In order to extract textual features and temporal correlation between replies [10]–[13], Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) and the attention mechanism are proposed to finish this classification task [14], [15] These models neglect the reading habits of the public. N. Bai et al.: Stochastic Attention CNN Model for Rumor Stance Classification broadcasted post, any word or phrase might become the key information for different readers to express their stances, and the traditional attention mechanism cannot completely reflect such habits. Different readers may use different keywords, and the stochastic attention mechanism is able to give stochastic initialized weights to different keywords Based on this random convolution kernel, almost any keyword is likely to be given a high activation probability, and the model can filter out the keywords that are not classification related through the full connection layer.

RELATED WORK

EVALUATION MEASURES

Findings

CONCLUSION AND FUTURE SCOPE