Stance Prediction for Russian: Data and Analysis

TL;DR

This paper introduces RuStance, a new Russian dataset for stance detection, and provides baseline classification approaches to advance research in identifying author attitudes in Russian social media and news comments.

Contribution

It presents the first openly-available Russian stance detection dataset and benchmarks for text classification in this language.

Findings

RuStance dataset covers multiple sources and stories

Baseline classification approaches established for Russian stance detection

Openly available dataset facilitates future research in Russian NLP

Abstract

Stance detection is a critical component of rumour and fake news identification. It involves the extraction of the stance a particular author takes related to a given claim, both expressed in text. This paper investigates stance classification for Russian. It introduces a new dataset, RuStance, of Russian tweets and news comments from multiple sources, covering multiple stories, as well as text classification approaches to stance detection as benchmarks over this data in this language. As well as presenting this openly-available dataset, the first of its kind for Russian, the paper presents a baseline for stance prediction in the language.