Towards Hybrid Intelligence in Journalism: Findings and Lessons Learnt from a Collaborative Analysis of Greek Political Rhetoric by ChatGPT and Humans

TL;DR

This study explores the use of ChatGPT alongside human experts to analyze Greek political speeches, highlighting the potential and limitations of AI-human collaboration in journalism and political discourse analysis.

Contribution

It presents an innovative hybrid intelligence approach combining AI and human expertise for political discourse analysis in a real-world electoral context.

Findings

ChatGPT effectively identified key political topics and sentiment.

Human oversight was crucial for accurate interpretation and validation.

The approach demonstrated potential for enhancing journalistic analysis with AI.

Abstract

This chapter introduces a research project titled "Analyzing the Political Discourse: A Collaboration Between Humans and Artificial Intelligence", which was initiated in preparation for Greece's 2023 general elections. The project focused on the analysis of political leaders' campaign speeches, employing Artificial Intelligence (AI), in conjunction with an interdisciplinary team comprising journalists, a political scientist, and data scientists. The chapter delves into various aspects of political discourse analysis, including sentiment analysis, polarization, populism, topic detection, and Named Entities Recognition (NER). This experimental study investigates the capabilities of large language model (LLMs), and in particular OpenAI's ChatGPT, for analyzing political speech, evaluates its strengths and weaknesses, and highlights the essential role of human oversight in using AI in journalism projects and potentially other societal sectors. The project stands as an innovative example of human-AI collaboration (known also as "hybrid intelligence") within the realm of digital humanities, offering valuable insights for future initiatives.