I am a Lecturer (Assistant Professor) in Computational Social Science at the University of Edinburgh School of Informatics, in the Institute for Language, Cognition and Computation. In my research, I primarily use computational methods from agent-based modelling, natural language processing and social network analysis to study social media and related technologies. A key focus of my research is to explore different aspects of social media, such as misinformation, hate speech, and the malicious use of automation (bots), as well as how social media can be used effectively for social good, such as in crisis communication. I also examine issues with these methods, from data collection practices to research data management.
At Edinburgh, I am a co-director of the SMASH group and part of the management team of the CDT in NLP. Before working here, I was a postdoctoral researcher at the University of Duisburg-Essen, where I also completed my PhD. I am a member of AIS, ACL and ACM and an Associate Editor of Business & Information Systems Engineering.
PhD, 2019
University of Duisburg-Essen
MSc in Computer Science, 2016
University of Münster
Exchange year, 2014-5
University of Strasbourg
BSc in Information Systems, 2013
University of Münster
Calabrese, Agostina; Bevilacqua, Michele; Ross, Björn; Tripodi, Rocco; Navigli, Roberto (2021). AAA: Fair Evaluation for Abuse Detection Systems Wanted. In WebSci ‘21: Proceedings of the ACM Web Science Conference, Southampton, United Kingdom, pp. 243–252.
Winter, Stephan; Neubaum, German; Stieglitz, Stefan; Ross, Björn (2021). #OpinionLeaders: A comparison of self-reported and observable influence of Twitter users. Information, Communication & Society (ICS) 24(11), pp. 1533–1550.
Jung, Anna-Katharina; Ross, Björn; Stieglitz, Stefan (2020). Caution: Rumors ahead – The debunking of false information on social media. Big Data & Society 7(2).
Ross, Björn; Pilz, Laura; Cabrera, Benjamin; Brachten, Florian; Neubaum, German; Stieglitz, Stefan (2019). Are social bots a real threat? An agent-based model of the spiral of silence to analyse the impact of manipulative actors in social networks. European Journal of Information Systems (EJIS), 28(4), pp. 394–412.
Agostina Calabrese is working on explainable models to detect abusive language online, while Eddie Ungless researches social biases in text analysis services. Sandrine Chausson examines the development of the environmental discourse using natural language processing and Seraphina Goldfarb-Tarrant (first supervisor: Adam Lopez) is working on fairness and bias in multilingual NLP. We are all part of the SMASH group, which I co-direct.
I am looking for more talented and motivated PhD students to join our group. If you are interested in pursuing a PhD and working with us, please familiarise yourself with my research and send me an email with your research interests and CV. If I think that it could be a good fit, we can then talk over Teams where I’ll be happy to answer any questions you might have.
Please also have a look at the relevant information on the web pages of the School, Institute and NLP CDT, where you can learn about the application process and funding options.
I am open to supervising self-proposed dissertation projects. If you are currently an Edinburgh student on one of our programmes and you would like to self-propose a project, please get in touch with me a few weeks before the deadline.
In the academic year 2021-22, I am teaching Text Technologies for Data Science (with Walid Magdy) at the University of Edinburgh School of Informatics. All course materials and recordings of live lectures can be found on the web page.