Motivation
Social networks have provided the opportunity for billions of users to interact with each other, exchange opinions, and share information. On the negative side, they are believed to provide a platform for the formation of polarized communities and social divides. In particular, biased news outlets and social media algorithms are suspected to fuel polarization and the formation of filter bubbles.
Questions
This project aims to study the following questions from a mathematical and algorithmic perspective:
- How polarized online communities are formed?
- What is the role of biased news media on polarization?
- Do social media recommendation algorithms boost user engagement with the cost of fuelling polarization?
Modelling
The project will use mathematical modelling and simulations to study the aforementioned questions. We rely on well-established opinion diffusion processes such as Friedkin-Johnsen model. In this model, each user is represented as a node in a graph and the edges between nodes correspond to friendship/following. Then, the opinion of nodes, expressed as a value between -1 and +1, is updated as a result of interaction with other users and following a predefined updating rule. We will advance the model to include the impact of external news sources and online recommendation algorithms. The above questions then can be rigorously studied leveraging various tools, from algorithm design, machine learning, network science, and combinatorial optimization.
Requirements
To complete the theoretical part of the project, the student should have a strong foundation in linear algebra and basic understanding of graph theory concepts.
The project will also include conducting experiments on real-world graph data to complement the theoretical findings. The student should be comfortable implementing experiments on graph data in the programming language of their choice.
Scope
This is best suitable for a 12-unit student project, or 24-unit honours project taken over a full academic year.
Related References
- Musco, Cameron, Christopher Musco, and Charalampos E. Tsourakakis. “Minimizing polarization and disagreement in social networks.” Proceedings of the 2018 World Wide Web Conference, 2018.
- Out, Charlotte, et al. “The Impact of External Sources on the Friedkin–Johnsen Model.” Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, 2024.
- Chitra, Uthsav, and Christopher Musco. “Analyzing the impact of filter bubbles on social network polarization.” Proceedings of the 13th International Conference on Web Search and Data Mining, 2020.
Contact
Supervisor: Ahad N. Zehmakan Email: ahadn.zehmakan@anu.edu.au.com
If you are interested, please write me an email, including (1) what aspects of this project interest you the most, (2) what type of research project you are looking for, 6-unit, 12-unit, or 24-unit, (3) a copy of your transcripts and/or CV, (4) any questions you may have.