Stance Detection: A Survey

What is it about?

This paper reviews the state-of-the-art in automatic stance detection. Stance detection is commonly defined as the automatic classification of the stance of the producer of a piece of text, towards a target, into one of these three classes: {Favor, Against, Neither}.” Our review paper includes definitions of related problems and concepts, classifications of the proposed approaches so far, descriptions of the relevant datasets and tools, and related outstanding issues.

Featured Image

Why is it important?

Stance detection is a recent and significant topic in natural language processing. Along with a number of related problems such as sentiment analysis, controversy detection, and argument mining, stance detection is a crucial process to elicit useful information from natural language texts, mostly from social media posts.