Political Social Media Analysis
We have been working with political scientists at the School of Social and Political Sciences focussing on opinion leadership among users in social networks, as well as the prevalence of electorally unsound events, such as reports of voting malpractice or election-related violence. In particular, during big political events such as the Scottish or EU Referendums, we addressed the question of who influences whom among national and international news producers by analysing the nature of the ties among media companies and media elites on Twitter, and the flow of information across these networks. Our work also studies the evolution of discussed topics on social media over time during elections or referendums, as well as classifying events detected from social media concerned with malpractice or violence. This project is currently being extended with the spread of misinformation online, including rumour, conspiracy and other falsehoods that pose a threat to democratic governance. In particular, the project asks to what extent do we observe political misinformation on social media; what types of misinformation exist; from what source(s) do misinformation arise; and how and why does misinformation propagate across individuals and communities?
Related Research & External Links
- Votes on Twitter: assessing candidate preferences and topics of discussion during the 2016 US presidential election, A Fang, P Habel, I Ounis, C Macdonald, 2018.
- Using word embeddings in twitter election classification, X Yang, C Macdonald, I Ounis, Information Retrieval Journal 21 (2-3), 183-207, 2018.
Transfer Learning for Multi-language Twitter Election Classification, Xiao Yang, Richard McCreadie, Craig Macdonald, Iadh Ounis, Proc. of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2017
- Anjie Fang, Craig Macdonald, Iadh Ounis, Philip Habel. Exploring Time-Sensitive Variational Bayesian Inference LDA for Social Media Data. In Proceedings of ECIR 2017.
- Anjie Fang, Philip Habel, Iadh Ounis and Craig Macdonald. Information Influence among Media, Policy Elites, Politicians and Citizens. In Proceedings of PolText 2016.
- Anjie Fang, Iadh Ounis, Philip Habel and Craig Macdonald. A User Study of Topic Coherence Metrics for Twitter Data. In Proceedings of ECIR 2016. Best paper honourable mention.
- Anjie Fang, Iadh Ounis, Philip Habel and Craig Macdonald. Topic-centric Classification of Twitter User's Political Orientation. In Proceedings of SIGIR 2015.
- Xiao Yang, Craig Macdonald, Iadh Ounis. Using Word Embeddings in Twitter Election Classification. In Proceedings of NeuIR at SIGIR 2016.
- Xiao Yang, Craig Macdonald, Iadh Ounis. Monitoring Electoral Violence through Social Media: A Machine Learning Approach. In Proceedings of the international conference on Computational Social Science 2016.