Skip to main content
Department of Information Technology

The Uppsala University Information Laboratory

Available thesis projects

At our lab we host a limited number of thesis projects. Those working on these projects become temporary members of the lab, are expected to complete the project under the agreed time constraints (typically 2.5 months for bachelors and 5 months for masters) and to actively participate in the lab activities, so that they can contribute to information sharing and knowledge development. Bachelor/Master students are expected to work full time on the project, that is, around 40 hours per week; we typically collaborate with maximum 3 students in parallel. A high degree of independence, a good level of ambition and good linguistic skills (English) are necessary, as all projects are part of the research activities of the lab and are expected to contribute to it with new knowledge, algorithms, code, etc. For most projects knowledge of C++ is expected. For master projects (and some of the bachelor projects) knowledge of data mining/machine learning is expected.

If you are interested, please send an email to matteo.magnani@it.uu.se with your transcript and a short CV or motivation.

Projects for the Spring 2021 (already assigned)

Algorithms for network co-evolution

Level: Bachelor/Master (multiple possible projects)
Tags: Algorithms, C++

Networks are used to model several types of data, from social networks to biological and brain networks. Numerous algorithms exist to generate synthetic network data with different properties (based on Erdos-Renyi and configuration models, rewiring, preferential attachment, etc.). These generative models are considered one of the core topics in the science of networks. This project concerns the extension of some of these approaches to networks where nodes can be connected by multiple types of relationships, as it is the case for example for social networks where nodes (individuals) can be friends, co-workers, family members, etc. This work can be based on the framework proposed in this paper and implemented in our network analysis library and also extend additional network formation approaches depending on the type of thesis (BSc/MSc) and number of students. The candidate(s) must have some basic knowledge of programming in C++.

Coordinated behaviours in the Swedish Facebook

Level: Bachelor or Master
Tags: Data analysis, network analysis

Social media platforms are inhabited by human users, completely automated users and a variety of other semi-automated accounts. These accounts participate in information spreading processes that may sometimes show coordination, in some cases obtained through connected automated accounts, and in some cases aiming at maliciously spreading specific (political) messages. The objective of this project is to replicate this study on the Swedish Facebook-sphere, study the results and (for a MSc) extend the methodology in the paper to consider additional types of coordination and additional methods for their discovery.

Analysis of visual political communication on YouTube

Level: Master (one or two people)
Tags: Algorithms, machine learning, deep learning

Recent years have seen a dramatic rise of visual politics, leading to the following research question: what is the role of visuals in the spread and ”stickiness” of political ideas online? To answer this question we need methods based on actual images that can handle scale. This project concerns the training of image classifiers and their application to YouTube data to identify the different types of climate change communication found across the world. An additional part of this project, to be performed by one or two different student(s), would also consider respectively the text associated to the videos and their networks (related videos, accounts commenting and sharing the videos) as part of the analysis of how climate change communication is organised on YouTube. Knowledge of Data Mining and Machine Learning are required. Knowledge of deep learning and previous experiences with deep learning libraries and training are meriting.

Updated  2021-01-21 14:36:57 by Matteo Magnani.