Stance Classification in Rumours as a Sequential Task Exploiting the Tree Structure of Social Media Conversations
This work addresses the problem of accurately classifying stances in social media rumours for NLP researchers, introducing a novel tree-based approach that is incremental but improves performance.
The paper tackled rumour stance classification on Twitter by modeling conversation threads as tree structures and using sequential classifiers, achieving significant improvements over non-sequential methods across eight datasets.
Rumour stance classification, the task that determines if each tweet in a collection discussing a rumour is supporting, denying, questioning or simply commenting on the rumour, has been attracting substantial interest. Here we introduce a novel approach that makes use of the sequence of transitions observed in tree-structured conversation threads in Twitter. The conversation threads are formed by harvesting users' replies to one another, which results in a nested tree-like structure. Previous work addressing the stance classification task has treated each tweet as a separate unit. Here we analyse tweets by virtue of their position in a sequence and test two sequential classifiers, Linear-Chain CRF and Tree CRF, each of which makes different assumptions about the conversational structure. We experiment with eight Twitter datasets, collected during breaking news, and show that exploiting the sequential structure of Twitter conversations achieves significant improvements over the non-sequential methods. Our work is the first to model Twitter conversations as a tree structure in this manner, introducing a novel way of tackling NLP tasks on Twitter conversations.