Issue agenda-setting in the voice to parliament referendum: using big data to explain voice discourse on traditional and social media

Abstract

ABSTRACT This article explores issue agenda-setting in Australia's 2023 Voice to Parliament referendum, analysing the dynamics of Yes and No campaigns in a diverse media ecosystem. We identify influential messages across this complex media environment using soft clustering of sentence embeddings from large language models (LLMs). Drawing on 3.3 million documents and over 10 million Voice specific sentences from mainstream and social media sources, we identify the narrative configurations of the campaigns, their audience size and engagement. Overall, the Yes campaign dominated with more diverse messaging and greater audience size and engagement than No. Yet, the No case prevailed. We find the narrower, mostly negative No campaign helped sustain the issue agenda both online and offline, forcing Yes to respond to it. The findings also challenge echo chamber theory, revealing most unique topics contained content from both #Yes and #No perspectives, indicating robust public engagement rather than isolated filter bubbles.