A Proposed Model for Persian Stance Detection on Social Media

Stance detection is a recent research topic that has become an emerging paradigm of the importance opinion-mining. It intended to determine author’s views toward specific or claim. important module in numerous applications such as fake news detection, argument search, claim validation, and author profiling. Despite considerable progress made this regard languages like English, unfortunately, we have not good some Persian, where are confronted with lack datasets area. In paper, two solutions used address issue: 1) use data augmentation 2) application different learning approaches (machine learning, deep transfer learning) meaningful combination their outcomes. The results show each these can only enhance stance performance, but when both combined, very significant improvement achieved.