Rumor classification is the process of categorizing the unreal information as rumor or true spreading in social media. Dissemination of rumors in social media is increasing due to ease of accessibility. Deep learning models are the widely used data-driven automatic rumor classification method. Although, deep learning models are solely focused on categorizing the rumor without analyzing and verifying the content of the misinformation properly.
An additional mechanism, a self-attentive network, is incorporated with a deep learning model for the complete verification of misinformation. A self-attentive network for rumor classification focuses on the reworking of misinformation and discovering subtle differences in the rumored content. The self-attentive network for rumor classification in social media improves the performance and accuracy of the classification model by reliably categorizing the rumor.