# KHAN: Knowledge-Aware Hierarchical Attention Networks for Accurate Political Stance Prediction

## TL;DR

This paper introduces KHAN, a knowledge-aware hierarchical attention network that improves political stance prediction by integrating external knowledge and analyzing contextual and tonal cues in news articles.

## Contribution

The paper proposes a novel approach combining hierarchical attention networks with external knowledge encoding, and constructs two separate political knowledge graphs for better stance prediction.

## Key findings

- KHAN outperforms existing methods in accuracy.
- KHAN demonstrates higher efficiency in processing.
- KHAN effectively fuses knowledge from two political knowledge graphs.

## Abstract

The political stance prediction for news articles has been widely studied to mitigate the echo chamber effect -- people fall into their thoughts and reinforce their pre-existing beliefs. The previous works for the political stance problem focus on (1) identifying political factors that could reflect the political stance of a news article and (2) capturing those factors effectively. Despite their empirical successes, they are not sufficiently justified in terms of how effective their identified factors are in the political stance prediction. Motivated by this, in this work, we conduct a user study to investigate important factors in political stance prediction, and observe that the context and tone of a news article (implicit) and external knowledge for real-world entities appearing in the article (explicit) are important in determining its political stance. Based on this observation, we propose a novel knowledge-aware approach to political stance prediction (KHAN), employing (1) hierarchical attention networks (HAN) to learn the relationships among words and sentences in three different levels and (2) knowledge encoding (KE) to incorporate external knowledge for real-world entities into the process of political stance prediction. Also, to take into account the subtle and important difference between opposite political stances, we build two independent political knowledge graphs (KG) (i.e., KG-lib and KG-con) by ourselves and learn to fuse the different political knowledge. Through extensive evaluations on three real-world datasets, we demonstrate the superiority of DASH in terms of (1) accuracy, (2) efficiency, and (3) effectiveness.