Open-Domain Event Graph Induction for Mitigating Framing Bias

TL;DR

This paper introduces a new framework for inducing neutral event graphs from news sources to reduce framing bias, enhancing trustworthy event understanding in open domains.

Contribution

It proposes a novel task of neutral event graph induction and a three-step framework utilizing GCNs to minimize framing bias in event graphs from multiple sources.

Findings

Effective reduction of framing bias demonstrated

Improved accuracy in event graph induction metrics

Framework outperforms baseline methods

Abstract

Researchers have proposed various information extraction (IE) techniques to convert news articles into structured knowledge for news understanding. However, none of the existing methods have explicitly addressed the issue of framing bias that is inherent in news articles. We argue that studying and identifying framing bias is a crucial step towards trustworthy event understanding. We propose a novel task, neutral event graph induction, to address this problem. An event graph is a network of events and their temporal relations. Our task aims to induce such structural knowledge with minimal framing bias in an open domain. We propose a three-step framework to induce a neutral event graph from multiple input sources. The process starts by inducing an event graph from each input source, then merging them into one merged event graph, and lastly using a Graph Convolutional Network to remove event nodes with biased connotations. We demonstrate the effectiveness of our framework through the use of graph prediction metrics and bias-focused metrics.