# Social context in political stance detection: Impact and extrapolation

## TL;DR

This paper shows how using a user's social network improves political stance detection and helps models work better in new countries and future events.

## Contribution

The novel contribution is using social context in stance detection to improve model extrapolation across countries and time.

## Key findings

- Using users' social networks improves in-country political stance detection performance.
- Leveraging social context enhances model extrapolation to new country contexts.
- Models with social context perform better on future events.

## Abstract

Stance detection is an important task with a wide range of high-impact social applications, including opinion polling and detecting propaganda, misinformation, and hate speech. In this work, we explore the performance and extrapolation power of political stance-detection models using an existing large-scale weakly-labeled Twitter dataset collected around the 2019 South American Protests. We construct transformer-based user and tweet encoders to embed users in a low-dimensional space using their posts and interactions. We then train heterogeneous graph attention networks to predict user stances and contrast their ability to extrapolate stance predictions to different country contexts and to future events. We find that leveraging users’ ego-network in political stance detection improves in-country model performance for every country we examine. More notably, we find that leveraging a user’s social context greatly enhances the ability of our stance detection models to extrapolate to new country contexts and future data.