DOI: 10.36190/2020.31

Published: 2020-06-05
Stance Classification for Rumour Verification in Social Media Conversations
Elena Kochkina, Maria Liakata, Arkaitz Zubiaga

Due to the risks posed by the proliferation of unverified content online, there is a need to develop automated methods to assist with the verification. Previous works have explored a variety of approaches to automated rumour verification. In particular, a discussion around a rumour, in which users may share their opinion and link extra relevant information, can be useful as rumours attracting a lot of sceptical and denying reactions are more likely to be proven false later. Here we discuss the relation between the tasks of rumour stance and veracity classification in social media conversations, giving the overview of recent advances leveraging that relation based on our work in this domain and experience from organising a shared task.