Summer Internship Projects 2025
Below are the available projects for our Summer Internship Program. Applicants indicate their preferred projects – up to three – in the application form.
Disease trajectories and co-morbidity networks
Research topic
Supervisor(s)
Project description
This project on comorbidity networks explores how diseases co-occur and interact within patient populations to reveal underlying structures of disease progression and multimorbidity patterns. By constructing networks where nodes represent diseases and links represent significant associations (e.g., relative risk or odds ratios), we can identify clusters of diseases that frequently co-occur. These networks, with their potential to enhance our understanding of disease trajectories, improve diagnosis, and offer insights into personalized healthcare.
Goal for the internship
Incorporate powerful network embedding techniques like node2vec or graph neural networks to transform these networks into low-dimensional representations; cluster patients based on these embedding.
Methods to be used
network embedding; node2vec or graph neural networks
Preferred academic background
- applied math / stats
- bioinformatics / public health
- data science
Preferred coding languages, packages, etc.
- Python
- R
Further reading
- Dervić, Elma, et al. “Unraveling cradle-to-grave disease trajectories from multilayer comorbidity networks.” npj Digital Medicine 7.1 (2024): 56
- Grover, Aditya, and Jure Leskovec. “node2vec: Scalable feature learning for networks.” Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining. 2016.
Data visualization: supply chains in the climate crisis
Research topic
Supervisor(s)
Project description
Develop innovative data visualizations to communicate insights from complexity science. The topic for visualization is Supply Chain Science, focusing on climate crisis. This project challenges you to transform intricate concepts into compelling visuals, making complex knowledge accessible to diverse audiences. You’ll hone skills in data analysis, visual design, and science communication while making a meaningful impact in the field of data visualization.
Goal for the internship
The project aims to tackle the challenge of visually communicating the complexities of supply chains and their impact on the climate crisis. By leveraging first-hand research from our scientific team, we will address how changes in supply chain dynamics contribute to environmental outcomes. The goal is to create visual narratives that make this information accessible, engaging, and actionable for a broad audience.
Methods to be used
web-based interactive visualizations with flexibility to integrate your artistic endeavors by experimenting with innovative data representations and/or exploring alternative formats like physicalizations or sonifications
Preferred academic background
any
Preferred coding languages, packages, etc.
any
Additional information
We encourage candidates to share the range of their ideas or motivations for this project. This flexibility allows you to express your interests and aspirations within the scope of our work. However, it’s perfectly fine if you don’t have any particular concepts in mind at this stage; we welcome all applicants regardless of their current thoughts, and we can shape the directions together.
How groups adapt to challenges
Research topic
Supervisor(s)
A member of the research group.
Project description
We want to understand how people in groups adapt to challenges by studying both their thinking and social interactions.
Human collectives adapt their cognitive strategies and social networks flexibly in response to diverse, evolving challenges. For instance, scientists continuously reconfigure their teams and methods of integrating information based on the topics they investigate. As citizens, we engage with various groups that employ distinct strategies to address issues such as economic development or climate change. This ability to adapt collectively has been critical to humanity’s success, but at times, collectives become stagnant, failing to respond effectively to the problems they face. Currently, there is no unified scientific framework to study collective adaptation, with its cognitive and social aspects often researched separately across disciplines. In our project, we aim to bridge this gap by developing computational models that integrate cognition and sociality, complemented by empirical data, including group experiments, natural language processing of large textual datasets, and longitudinal surveys. This approach will allow us to explore the dynamics between social learning, belief formation, and collective problem-solving, helping to explain why groups sometimes fail to adapt and how to prevent societal stagnation.
Goal for the internship
Understand how collectives adapt their social learning strategies and network structures in response to multiple problems that change over time.
Methods to be used
integration of computational modeling, natural language processing (NLP), and empirical research
Preferred academic background
- applied math / stats
- computer science
- data science
- social science / computational social science
Preferred coding languages, packages, etc.
- Python
- R
- MATLAB
- SPSS, STATA or similar
Further reading
- Galesic, M., et al. (2023). Beyond collective intelligence: Collective adaptation. Journal of The Royal Society Interface, 20, 20220736.
Inferring DAO roles from communication patterns
Research topic
Supervisor(s)
Project description
The goal of this project is to leverage potentials of LLMs in exploring whether members of Decentralised Autonomous Organisations (DAOs) in the Decentralized Finanace (DeFi) space can be assigned certain user roles (e.g., domain experts, insight provokers, stewards, token chasers, passive observers etc.) depending on their communication patterns and engagement levels in public online discussions of DAO proposals.
Goal for the internship
- Define which member roles exist in DAO communities in the DeFi space.
- Determine if these roles can be identified for certain users based on their interactions in public online discussions and forums.
Methods to be used
web scraping, LLM & natural language processing, sentiment analysis
Preferred academic background
- computer science
- data science
Preferred coding languages, packages, etc.
- Python
- R
Further reading
- Werbach, Kevin, et al. “Blockchain Governance in the Wild.” (2024).
- Shah, Chirag, et al. “Using large language models to generate, validate, and apply user intent taxonomies.” arXiv preprint arXiv:2309.13063 (2023).
Additional information
Students should have a basic familiarity with DeFi & DAOs.
Influence of misinformation in the cryptosphere
Research topic
Supervisor(s)
Project description
We live in an era of information abundance where it is challenging to assess the accuracy of the content that is circulating in the public space. A large part of it is misinformation, which can sometimes be spread intentionally. Spreading untruthful information is a complex process, often involving multiple media channels like online social media, traditional media, messaging platforms, web portals, etc. Researchers have studied the spreading of misinformation on various topics, such as political elections, COVID-19, and armed conflicts throughout the world. Many studies have also investigated the effects of misinformation on financial systems, especially for traditional assets, but the realm of digital assets has still not been explored enough. The overall goal of the project is to study the presence of misinformation and its influence in the sphere of cryptocurrencies.
Goal for the internship
We will examine the misinformation circulating on online social media, such as “pump and dump” scams, and investigate its effects on cryptocurrency prices and crypto-exchange dynamics.
Methods to be used
various techniques from data science, network science, machine learning, and natural language processing, as well as working with large datasets
Preferred academic background
any
Preferred coding languages, packages, etc.
- Python
Further reading
- Mirtaheri, Mehrnoosh, et al. “Identifying and analyzing cryptocurrency manipulations in social media.” IEEE Transactions on Computational Social Systems 8.3 (2021): 607-617.
Additional information
Students should have knowledge and interest in the fields relevant to the project (see “Methods to be used”).
Tracing the origins of political contributions
Research topic
Foundations of Complex Systems [Principles of Emergent Things] • Eddie Lee
Supervisor(s)
Eddie Lee
Project description
The US presidential election in 2025 has attracted billions of dollars from individuals and companies. Other federal and state elections also attract many millions of dollars in contributions. Where does this money come from? How are donations related to one another, and how do donors decide when to donate?
Goal for the internship
- We will map the structure of donation networks that are recovered from publicly available data from the Federal Election Commission.
- We will explore the patterns behind donations in a few key historical elections to map the networks of donors and the strategic dynamics behind donations.
- We will use such information to develop mathematical models of collective decisions.
Methods to be used
scraping large data sets, network science, statistical physics
Preferred academic background
- applied math / stats
- data science
- physics
- social science / computational social science
Preferred coding languages, packages, etc.
- Python
- Julia
Further reading
- Lee, Edward D., Chase P. Broedersz, and William Bialek. “Statistical mechanics of the US Supreme Court.” Journal of Statistical Physics 160 (2015): 275-301.
Additional information
The intern will ideally be familiar with scraping large datasets, network science and statistical physics (or have a strong mathematical background), and should be interested in taking the initiative to drive a project forward.