Recommended posts, products, and connections – Have you ever wondered why your social media feed seems to know you so well? This almost magically fitting content is convenient for many. Yet, it raises fundamental concerns: “filter bubbles” isolate consumers from diverse perspectives, confirmation bias reinforces extreme viewpoints, and not to mention the legitimate concerns about data privacy and the lack of transparency. Up to this day, we can only measure the effect of recommender algorithms on society after they have already made an impact. This is due to the ongoing interaction between human behavior and these algorithms. Of course, this challenges the development of more balanced and fair technologies.

Stefan Neumann addresses this unresolved issue with his new Vienna Research Group on “Algorithmic Foundations of Social Network Analysis”. He aims to study the effects of recommender systems in social networks before they are deployed – to minimize negative societal effects and contribute to the effective regulation of social media algorithms. The Vienna Research Group will be established at TU Wien Informatics, funded by the 14th Vienna Research Groups for Young Investigators Grant 2023 by WWTF. The grant supports outstanding young international researchers to establish a new research group at esteemed Viennese research institutions, providing up to €1.6 million per group for up to 8 years.

Stefan Neumann’s group will deal with three significant research endeavors: First, they’ll create new methods to mathematically analyze how recommender systems and polarization interact in online social networks. This involves adapting opinion formation models from sociology to fit user interactions online and examining computational aspects, like efficient simulation and optimization issues. Second, they will deal with adversaries’ impact on online social networks. This is motivated by recent societal developments, like state actors using bots and disinformation campaigns to influence elections in opposing countries. The group aims to understand the power of such adversaries and characterize how recommender systems must be modified and improved to mitigate such attacks. Third, the group will consider applications and further extensions of their models. They will study how user opinions can be utilized to aid fine-grained information campaigns, such as by governments who wish to inform their population about new policies or advertisers who want to sell their products.

About Stefan Neumann

Stefan Neumann is currently a tenure-track assistant professor at KTH. He is an expert in data science and social network analysis. In data science, his work involves creating reliable algorithms, focusing on theoretical methods that identify and utilize data patterns. In social network analysis, Neumann examines the effects of specific interventions, like Facebook’s timeline algorithm, on network polarization and disagreement.

Before his current role, Neumann was a postdoctoral researcher at KTH in the group of Aris Gionis. He earned his Ph.D. from the University of Vienna under the supervision of Monika Henzinger and spent six months at Brown University with Eli Upfal. The Austrian Computer Society honored his Ph.D. thesis with the Heinz Zemanek Award, and he received the Award of Excellence from the Austrian federal government. His academic foundation was laid at Saarland University and Max Planck Institute for Informatics, where he earned his Master’s degree, collaborating with Pauli Miettinen and Jilles Vreeken.

Curious about our other news? Subscribe to our news feed, calendar, or newsletter, or follow us on social media.