Embedding-based Approaches to Hyperpartisan News Detection

2025-01-02

AI Summary

This paper addresses the problem of escalating political polarization exacerbated by hyperpartisan news. We propose an end-to-end deep learning method to automatically detect news articles exhibiting extreme political bias and intent to deepen societal division. Methodologically, we introduce the first integration of pretrained ELMo embeddings with a bidirectional LSTM—eschewing handcrafted rules and shallow features (e.g., n-grams, sentiment lexicons)—to enable fine-grained, semantics-aware political stance modeling. Evaluated on a standard benchmark dataset via 10-fold cross-validation, our model achieves 83% accuracy, substantially outperforming conventional baselines. Our key contributions are: (1) the first ELMo-BiLSTM framework for hyperpartisan news detection; (2) empirical validation of deep semantic representations for robust political bias identification; and (3) a reproducible, low-dependency analytical tool to support algorithm-driven governance of political communication.

Technology Category

Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)Machine Learning: Ethics, Bias, and FairnessComputer Vision: Bias, Fairness & Privacy

Application Category

Web Mining and Content Analysis: Large pretrained models with web dataSocial Networks and Social Media: Fairness and bias in social network and social media analysisGraph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

In this paper, we describe our systems in which the objective is to determine whether a given news article could be considered as hyperpartisan. Hyperpartisan news is news that takes an extremely polarized political standpoint with an intention of creating political divide among the public. We attempted several approaches, including n-grams, sentiment analysis, as well as sentence and document representation using pre-tained ELMo. Our best system using pre-trained ELMo with Bidirectional LSTM achieved an accuracy of 83% through 10-fold cross-validation without much hyperparameter tuning.

Problem

• Partisan News Detection
• Political Polarization Analysis
• Bias Identification

Innovation

• n-grams
• Sentiment Analysis
• ELMo with BiLSTM