Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AI as a Tool for Fair Journalism: Case Studies from Malta

Dylan Seychell, Gabriel Hili, Jonathan Attard, Konstantinos Makantatis

TL;DR

This paper investigates AI as a tool to promote fair journalism by presenting two Malta-based case studies on bias analysis in news content. It develops an article-bias analysis pipeline leveraging NER, keyword extraction, sentiment, and image-text matching, and a video-bias pipeline with OCR-name extraction and face tracking to quantify on-screen exposure. Evaluations on six Maltese newspapers (800 articles each) and 215 news videos (8.48 hours) reveal nuanced relationships between sentiment and image relevance and identify practical configurations (e.g., 1-s interval, 640x360) for reliable measurements. The work emphasizes transparency, explainability, and alignment with COE guidelines to help journalists reduce bias and enhance media trust.

Abstract

In today`s media landscape, the role of Artificial Intelligence (AI) in shaping societal perspectives and journalistic integrity is becoming increasingly apparent. This paper presents two case studies centred on Malta`s media market featuring technical novelty. Despite its relatively small scale, Malta offers invaluable insights applicable to both similar and broader media contexts. These two projects focus on media monitoring and present tools designed to analyse potential biases in news articles and television news segments. The first project uses Computer Vision and Natural Language Processing techniques to analyse the coherence between images in news articles and their corresponding captions, headlines, and article bodies. The second project employs computer vision techniques to track individuals` on-screen time or visual exposure in news videos, providing queryable data. These initiatives aim to contribute to society by providing both journalists and the public with the means to identify biases. Furthermore, we make these tools accessible to journalists to improve the trustworthiness of media outlets by offering robust tools for detecting and reducing bias.

AI as a Tool for Fair Journalism: Case Studies from Malta

TL;DR

This paper investigates AI as a tool to promote fair journalism by presenting two Malta-based case studies on bias analysis in news content. It develops an article-bias analysis pipeline leveraging NER, keyword extraction, sentiment, and image-text matching, and a video-bias pipeline with OCR-name extraction and face tracking to quantify on-screen exposure. Evaluations on six Maltese newspapers (800 articles each) and 215 news videos (8.48 hours) reveal nuanced relationships between sentiment and image relevance and identify practical configurations (e.g., 1-s interval, 640x360) for reliable measurements. The work emphasizes transparency, explainability, and alignment with COE guidelines to help journalists reduce bias and enhance media trust.

Abstract

In today`s media landscape, the role of Artificial Intelligence (AI) in shaping societal perspectives and journalistic integrity is becoming increasingly apparent. This paper presents two case studies centred on Malta`s media market featuring technical novelty. Despite its relatively small scale, Malta offers invaluable insights applicable to both similar and broader media contexts. These two projects focus on media monitoring and present tools designed to analyse potential biases in news articles and television news segments. The first project uses Computer Vision and Natural Language Processing techniques to analyse the coherence between images in news articles and their corresponding captions, headlines, and article bodies. The second project employs computer vision techniques to track individuals` on-screen time or visual exposure in news videos, providing queryable data. These initiatives aim to contribute to society by providing both journalists and the public with the means to identify biases. Furthermore, we make these tools accessible to journalists to improve the trustworthiness of media outlets by offering robust tools for detecting and reducing bias.
Paper Structure (17 sections, 3 figures, 3 tables)

This paper contains 17 sections, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Background and Literature Review
  3. AI for Media Bias Mitigation
  4. Vision Language Pre-training
  5. Media Bias Analysis in Videos
  6. Proposed AI in Journalism Tools
  7. News Articles Analysis
  8. News Video Analysis
  9. Name Extraction
  10. Face Detection, Encoding, and Recognition
  11. Face Tracking
  12. Evaluation
  13. Evaluating the News Article Analysis
  14. Evaluating the News Video Analysis
  15. Metrics
  16. ...and 2 more sections

Figures (3)

  • Figure 1: Diagram showing the data transformation pipeline of the news articles data.
  • Figure 2: A frame timeline showing three people who appeared, along with the real‐time analysis annotations. The generated analysis timeline can be seen in the leftmost timeline in Figure \ref{['fig:analysis_timeline']}.
  • Figure 3: The analysis timeline showing occuring individuals by their names inclduing their timestamps and durations.