On Representation Learning for Scientific News Articles Using Heterogeneous Knowledge Graphs

TL;DR

This paper explores the use of heterogeneous knowledge graphs and graph neural networks to improve the representation and credibility assessment of scientific news articles by modeling their relationships with cited research and authors.

Contribution

It introduces a methodology for representing scientific news using heterogeneous knowledge graphs and compares three graph neural network models for link prediction tasks.

Findings

HGT outperforms R-GCN and HetGNN in link prediction accuracy.

Graph neural networks effectively model relationships in scientific news data.

Results demonstrate potential for credibility assessment and knowledge tracing.

Abstract

In the era of misinformation and information inflation, the credibility assessment of the produced news is of the essence. However, fact-checking can be challenging considering the limited references presented in the news. This challenge can be transcended by utilizing the knowledge graph that is related to the news articles. In this work, we present a methodology for creating scientific news article representations by modeling the directed graph between the scientific news articles and the cited scientific publications. The network used for the experiments is comprised of the scientific news articles, their topic, the cited research literature, and their corresponding authors. We implement and present three different approaches: 1) a baseline Relational Graph Convolutional Network (R-GCN), 2) a Heterogeneous Graph Neural Network (HetGNN) and 3) a Heterogeneous Graph Transformer (HGT). We test these models in the downstream task of link prediction on the: a) news article - paper links and b) news article - article topic links. The results show promising applications of graph neural network approaches in the domains of knowledge tracing and scientific news credibility assessment.