And the final speaker in this final AoIR 2024 conference session is the excellent Fabio Giglietto, whose focus is on coding Italian news data using Large Language Models. This worked with some 85,000 news articles shared on Facebook during the 2018 and 2022 Italian elections, and first classified such URLs as political or non-political; it then produced and clustered text embeddings for these articles, and used GPT-4-turbo to classify the dominant topics in these clusters.
The next speaker in this final AoIR 2024 conference session is the great Hendrik Meyer, whose interest is in detecting stances in climate change coverage. This focusses especially on climate change debates in German news media, focussing on climate protests, discussions about speed limits, and discussions about heating and heat pump regulations.
The next speaker in this session at the AoIR 2024 conference is my QUT colleague Tariq Choucair, whose focus is especially on the use of LLMs in stance detection in news content. A stance is a public act by a social actors, achieved dialogically through communication, which evaluates objects, positions the self and other subjects, and aligns with other subjects within a sociocultural field.
The second speaker in this final session at the AoIR 2024 conference is Bruna Silveira de Oliveira, whose focus is on using LLMs to study content in the Brazilian manosphere. Extremist groups in this space seek legitimisation, and the question here is whether LLMs can be used productively to analyse their posts.
The final (!) session at this wonderful AoIR 2024 conference is on content analysis, and starts with Ahrabhi Kathirgamalingam. Her interest is especially on questions of agreement and disagreement between content codings; the gold standard here has for a long time been intercoder reliability, but this tends to presume a single ground truth which may not exist in all coding contexts.
I presented in and chaired the Saturday morning session at the AoIR 2024 conference, which was on polarisation in news publishing and engagement, so no liveblogging this time. However, here are the slides from the three presentations that our various teams and I were involved in.
We started with my QUT DMRC colleague Laura Vodden, who discussed our plans for manual and automated content coding of news content for indicators of polarisation, and especially highlighted the surprising difficulties in getting access to quality and comprehensive news content data:
I presented the next paper, which explored the evidence for polarisation in news recommendations from Google News, building on our Australian Search Experience project in the ARC Centre of Excellence for Automated Decision-Making and Society (ADM+S):