Media bias and electoral discourse

Abstract

This study employs quantitative and artificial intelligence methods to scrutinize media coverage during an election campaign. Employing TF, TF*IDF, and word2vec for text quantification and vectorization, alongside UAMP and t-SNE for cluster analysis, we examine how certain terms are utilized across media outlets and their semantic associations. Our findings reveal a tendency for media to link certain candidates or parties with political extremes, violence, and negativity, often overshadowing substantive political discourse. Notably, coverage predominantly focuses on major parties and polarizing factions. Campaign events receive more attention than policy proposals, which are often neglected. These insights align with prior qualitative studies, demonstrating the efficacy of our quantitative approach in expanding sample size, reducing analysis time, and revealing nuanced patterns not readily apparent through traditional methodologies. This study contributes to a deeper understanding of media dynamics during election cycles and underscores the value of quantitative methods in media analysis.