1Theory-inspired Recommender Systems
Our aim is to design, develop and evaluate novel recommender systems that are based on theories and models of human behaviour.
We study potentially harmful effects of these systems such as filter bubbles and biases that impact users of recommender systems. Novel algorithms are used to enrich our recommender framework ScaR.
2Dynamics in Social Networks
Our goal is to shape information diffusion in complex networks. We model conflict and cooperation dynamics, spread of misinformation, trust.
We extend our work on opinion dynamics in online social networks with mechanisms to enhance consensus formation.
3Policy Development and Tools for Open Science
Our goal is to support evidence-based policy making to facilitate the transition to open science at a European, national, and institutional level.
We strive to understand the factors influencing scientific workflows and which tools and policy recommendations may help open up the review-disseminate-assess phases of the research lifecycle.
- Recommender systems
- Predictive modeling
- Social network analysis
- Machine Learning & data mining
- Web science
- Social data science
- Open science
- Information quality and credibility
- User modeling
- Collaborative systems
Dr. Dominik Kowald
Research Area Manager Social Computing
Operations Area Manager Social Computing