Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Balancing Transparency and Accuracy: A Comparative Analysis of Rule-Based and Deep Learning Models in Political Bias Classification

Manuel Nunez Martinez, Sonja Schmer-Galunder, Zoey Liu, Sangpil Youm, Chathuri Jayaweera, Bonnie J. Dorr

TL;DR

The opaque architecture of a deep learning model is contrasted with the transparency of a linguistically informed rule-based model, showing that the rule-based model performs consistently across different data conditions and offers greater transparency, whereas the deep learning model is dependent on the training set and struggles with unseen data.

Abstract

The unchecked spread of digital information, combined with increasing political polarization and the tendency of individuals to isolate themselves from opposing political viewpoints, has driven researchers to develop systems for automatically detecting political bias in media. This trend has been further fueled by discussions on social media. We explore methods for categorizing bias in US news articles, comparing rule-based and deep learning approaches. The study highlights the sensitivity of modern self-learning systems to unconstrained data ingestion, while reconsidering the strengths of traditional rule-based systems. Applying both models to left-leaning (CNN) and right-leaning (FOX) news articles, we assess their effectiveness on data beyond the original training and test sets.This analysis highlights each model's accuracy, offers a framework for exploring deep-learning explainability, and sheds light on political bias in US news media. We contrast the opaque architecture of a deep learning model with the transparency of a linguistically informed rule-based model, showing that the rule-based model performs consistently across different data conditions and offers greater transparency, whereas the deep learning model is dependent on the training set and struggles with unseen data.

Balancing Transparency and Accuracy: A Comparative Analysis of Rule-Based and Deep Learning Models in Political Bias Classification

TL;DR

The opaque architecture of a deep learning model is contrasted with the transparency of a linguistically informed rule-based model, showing that the rule-based model performs consistently across different data conditions and offers greater transparency, whereas the deep learning model is dependent on the training set and struggles with unseen data.

Abstract

The unchecked spread of digital information, combined with increasing political polarization and the tendency of individuals to isolate themselves from opposing political viewpoints, has driven researchers to develop systems for automatically detecting political bias in media. This trend has been further fueled by discussions on social media. We explore methods for categorizing bias in US news articles, comparing rule-based and deep learning approaches. The study highlights the sensitivity of modern self-learning systems to unconstrained data ingestion, while reconsidering the strengths of traditional rule-based systems. Applying both models to left-leaning (CNN) and right-leaning (FOX) news articles, we assess their effectiveness on data beyond the original training and test sets.This analysis highlights each model's accuracy, offers a framework for exploring deep-learning explainability, and sheds light on political bias in US news media. We contrast the opaque architecture of a deep learning model with the transparency of a linguistically informed rule-based model, showing that the rule-based model performs consistently across different data conditions and offers greater transparency, whereas the deep learning model is dependent on the training set and struggles with unseen data.

Paper Structure

This paper contains 23 sections, 22 figures, 8 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Data Querying and Setup
  4. Data Sourcing
  5. Exploratory Data Analysis
  6. Model Implementations
  7. Rule-Based Sentiment Analysis Model
  8. Coreference Resolution
  9. Dependency Parsing and Part of Speech Reference Resolution
  10. Sentiment Vectorization and Cosine Distance Computation
  11. Convolutional NN Model
  12. Results
  13. Sentiment Analysis Model: Evaluation
  14. Convolutional NN Model: Evaluation
  15. Application and Insights: CNN and FOX
  16. ...and 8 more sections

Figures (22)

  • Figure 1: Comparison of Rule-based and Convolutional NN models: CNN and FOX news articles serve as external, unseen datasets for the Convolutional NN model. The rule-based model determines political bias using three linguistic features.
  • Figure 2: News outlet spectrum selected from Media Bias Chart 10.0 OKC2022: left, center, right
  • Figure 3: Theoretical mapping of left-vs-right space where an input articles positioned.
  • Figure 4: Dep Tree: Algorithm Walk-through
  • Figure 5: Top 25 Influential Terms in Right Class Classification
  • ...and 17 more figures