The workshops are held on 19.9. from 10–12 and 13–14 at HSSH Seminar room 524, Fabianinkatu 24 A, 5th floor and they are intended for researchers (including PhD researchers).
The workshops are unfortunately full – thank you for your interest!
10–12
Axel Bruns: An Introduction to Practice Mapping
This workshop introduces the analytical approach of practice mapping (Bruns et al., 2024), using vector embeddings of networked actions and interactions to map commonalities and disjunctures in the practices of social media users, as a framework for methodological advancement beyond the limitations of conventional network analysis and visualisation. In particular, this innovative methodological framework has the potential to incorporate multiple distinct modes of interaction into a single practice map, can be further enriched with account-level attributes such as information gleaned from textual analysis, profile information, available demographic details, and other features, and can be applied even to a cross-platform analysis of communicative patterns and practices. Using a sample dataset, this workshop introduces the basic steps in practice mapping and provides an outlook on how it may be applied in the study of complex communicative processes in social media.
Bruns, A., Kasianenko, K., Suresh, V. P., Dehghan, E., & Vodden, L. (2024, July 8). Untangling the Furball: A Practice Mapping Approach to the Analysis of Multimodal Interactions in Social Networks. arXiv. Retrieved from http://arxiv.org/abs/2407.05956 arXiv:2407.05956 [cs]
13–15
Laura Vodden: Automating News Content Coding with Large Language Models
Social science scholars are increasingly adopting computational methods in their research. LLMs offer accessibility and a potentially cost-effective solution for extending the scope of social science research; however, their opaque and non-deterministic nature poses a challenge for evaluating their outputs and ensuring research integrity. This workshop will demonstrate how to use OpenAI’s GPT models for various content coding tasks, using news articles covering the COP26 and COP27 events. This workshop will see participants generate a ‘gold standard’ dataset, run a prompt using GPT to code a small set of news articles, and compare results between human codes and LLM outputs - and will encourage participants to think about the potential of LLMs in social science research.
Participants will require:
- a laptop with internet connection
- an OpenAI account/API Key (potential to use the free credits available with a new account)
- a Google account (for accessing a Google Colab notebook)
- no programming experience necessary as the Colab Notebook will be pre-set up for participants to run code
-
Axel Bruns is an Australian Laureate Fellow and Professor in the Digital Media Research Centre at Queensland University of Technology in Brisbane, Australia, and a Chief Investigator in the ARC Centre of Excellence for Automated Decision-Making and Society. His books include Are Filter Bubbles Real? (2019) and Gatewatching and News Curation: Journalism, Social Media, and the Public Sphere (2018), and the edited collections Digitizing Democracy (2019), the Routledge Companion to Social Media and Politics (2016), and Twitter and Society (2014). His current research focusses on the study of public communication in digital and social media environments, with particular attention to the dynamics of polarisation, partisanship, and problematic information, and their implications for our understanding of the contemporary public sphere; his work draws especially on innovative new methods for analysing ‘big social data’. He served as President of the Association of Internet Researchers in 2017–19. His research blog is at http://snurb.info/, and he posts at @snurb_dot_info / @snurb@aoir.social / @snurb.bsky.social.
Laura Vodden is a Data Scientist and PhD candidate at the Digital Media Research Centre (DMRC), Queensland University of Technology, in Brisbane, Australia. Laura's research interests include interrogating framing in news media and the exploration of embedded social bias in machine learning and artificial intelligence models. In her PhD research, Laura is developing a software pipeline and an analytical framework designed to assist researchers in the effective utilisation of Large Language Models (LLMs) across various social science research tasks.