Artificial Intelligence in Brazilian News: A Mixed-Methods Analysis

TL;DR

Brazilian news coverage of AI is dominated by topics related to applications in the workplace and product launches, with limited space for societal concerns, which mostly focus on deepfakes and electoral integrity.

Abstract

The current surge in Artificial Intelligence (AI) interest, reflected in heightened media coverage since 2009, has sparked significant debate on AI's implications for privacy, social justice, workers' rights, and democracy. The media plays a crucial role in shaping public perception and acceptance of AI technologies. However, research into how AI appears in media has primarily focused on anglophone contexts, leaving a gap in understanding how AI is represented globally. This study addresses this gap by analyzing 3,560 news articles from Brazilian media published between July 1, 2023, and February 29, 2024, from 13 popular online news outlets. Using Computational Grounded Theory (CGT), the study applies Latent Dirichlet Allocation (LDA), BERTopic, and Named-Entity Recognition to investigate the main topics in AI coverage and the entities represented. The findings reveal that Brazilian news coverage of AI is dominated by topics related to applications in the workplace and product launches, with limited space for societal concerns, which mostly focus on deepfakes and electoral integrity. The analysis also highlights a significant presence of industry-related entities, indicating a strong influence of corporate agendas in the country's news. This study underscores the need for a more critical and nuanced discussion of AI's societal impacts in Brazilian media.

Figures (8)

• Figure 1: Google Trends scores for AI and Media Cloud ratio of news mentioning AI in the US and Brazil.
• Figure 2: Number of topics ($k$) and coherence score ($c_v$). Highest: $k=19, c_v=0.5913$.
• Figure 3: LDA: Distribution of articles underscores the thematic alignment of different media types with certain topics. Lighter colors correspond to a higher percentage of texts in a topic within a media category. Topics with too few articles (5, 9, 15, 18) were removed.
• Figure 4: The Intertopic Distance Map displays the thematic spaces of LDA-generated topics in a two-dimensional plane, where each bubble's size reflects the topic's prevalence. Distances between bubbles represent differentiation between them. Closer bubbles have more thematic overlap.
• Figure 5: Daily volume of articles about AI displays surges depending on particular news events.