Abstract:
Frame analysis is a content analysis method that seeks to understand how narratives are shaped and presented to audiences, via their framing in communication. Manual frame analysis is a time- and labour-intensive task, which limits the scope of empirical research (Kuang et al., 2024; Walter & Ophir, 2019). These constraints, along with the increasing volume of text-based data, have prompted researchers to employ computational methods such as topic modelling and network analysis, to analyse frames at scale (Kermani et al., 2023; Kroon et al., 2023). Such methods offer the advantage of processing large volumes of media content, but currently do not, by themselves, sufficiently capture media frames (Ali & Hassan, 2022).
Large Language Models (LLMs) have the potential to bridge this gap and expand the scope of content analysis in general and frame analysis specifically. Several authors (e.g. Alizadeh et al., 2025) have identified the potential value of LLMs in frame analysis, but presently there is no established methodology available for applying LLMs to analyse framing in the news. This presentation shows how LLMs can be used to inductively extract frames from news content on a range of pressing social issues, and, importantly, enhance manual approaches to frame analysis by fostering reflexivity throughout the coding process and necessitating renewed engagement with questions of bias and truth in qualitative research.
Bio:
Laura Vodden is a Data Scientist and PhD Candidate the Digital Media Research Centre at the Queensland University of Technology. She has an interdisciplinary academic background with qualifications in archaeology, geological science, and data science. Since joining the DMRC in 2021, she has supported the methodological and software development, and data acquisition for Professor Axel Bruns’s Australian Laureate Fellowship project, Determining the Drivers and Dynamics of Partisanship and Polarisation in Online Public Debate. Laura’s research is situated at the intersection of artificial intelligence, computational methods, content analysis, and gender studies, with a particular focus on the mechanisms through which gender is constructed and ‘policed’ by news media. Her work develops a methodological framework for the use of Large Language Models (LLMs) in supporting qualitative research, contributing to ongoing scholarly debates surrounding the integration of AI in the social sciences. This includes critical engagement with questions of methodological rigour, epistemological validity, and the ethical implications of LLM-assisted research.