Stance Detection Based on User Feature Fusion

Rapid development of the Internet has contributed to the widespread adoption of social network platforms. Network media plays an important role in the process of public opinion dissemination and bears significant social responsibility. Public opinion mining is of great significance for online media to improve the quality of content provision and enhance media credibility. How to make full use of user-generated content is the key to improving the accuracy of position detection tasks. In this paper, we proposed a stance detection model based on user feature fusion by using comments of netizens in false news events on Weibo as research content. The method of feature fusion is adopted to integrate vectors including user sentiment, cognitive features, and text feature at the feature layer for model training and position prediction. The model is evaluated on a dataset of related microblog comments in false news. The result shows that our proposed method has a certain improvement in the effect of stance detection.