X-Stance: A Multilingual Multi-Target Dataset for Stance Detection

Abstract

We extract a large-scale stance detection dataset from comments written by candidates of elections in Switzerland. The dataset consists of German, French and Italian text, allowing for a cross-lingual evaluation of stance detection. It contains 67 000 comments on more than 150 political issues (targets). Unlike stance detection models that have specific target issues, we use the dataset to train a single model on all the issues. To make learning across targets possible, we prepend to each instance a natural question that represents the target (e.g. "Do you support X?"). Baseline results from multilingual BERT show that zero-shot cross-lingual and cross-target transfer of stance detection is moderately successful with this approach.

arXiv commentSwissText + KONVENS 2020. Data and code are available at https://github.com/ZurichNLP/xstance

Cited by in corpus (7)

• Stance Detection on Social Media: State of the Art and Trends
• Automated stance detection in complex topics and small languages: the challenging case of immigration in polarizing news media
• Towards Analyzing the Bias of News Recommender Systems Using Sentiment and Stance Detection
• Migration Reframed? A multilingual analysis on the stance shift in Europe during the Ukrainian crisis
• ORCHID: A Chinese Debate Corpus for Target-Independent Stance Detection and Argumentative Dialogue Summarization
• Deep Natural Language Feature Learning for Interpretable Prediction
• Political Advertising Dataset: the use case of the Polish 2020 Presidential Elections