Christine Bauer is an Assistant Professor at the Human-Centered Computing group at the Department of Information and Computing Sciences at Utrecht University.
Her research activities center on interactive intelligent systems where she integrates research on intelligent technologies, the interaction of humans with the intelligent system, as well as their interplay. Thereby, she takes a human-centered computing approach, where technology follows humans’ and society’s needs. Central themes in her research are context and context-adaptivity. Recently, she focuses on context-aware recommender systems and concentrates on recommender systems in the music and media sector in particular. Core interests in her research activities are fairness and multi-method evaluation.
Doctoral degree in Social and Economic Sciences (Business Informatics), 2009
University of Vienna, Austria
MSc in Business Informatics, 2011
TU Wien, Austria
Diploma (equivalent to Master degree) in International Business Administration, 2002
University of Vienna, Austria
Study of Jazz Saxophone
Konservatorium der Stadt Wien, Austria
Interactive intelligent systems
at the intersection of human-centered computing, data science, and artificial intelligence
24 different courses across 15 institutions
RecSys Summer School, Italian National PhD Program of AI
Tutorials at UMAP and ISMIR
Supervision of >70 theses
AE at TORS
PC Co-Chair (e.g., RecSys, CHI, CIKM)
Meta-Reviewer (e.g., CHI, UMAP, ISMIR)
Reviewer for >25 journals and >100 conferences
Research experience in 4 countries (AT, DE, NL, US)
Teaching experience in 6 countries (AT, DE, IT, NL, SE, US)
Repeatedly speaker and panelist at non-scientific events (e.g., Ars Electronica Festival, Dutch Media Week, VUT Indie Days)
Substantial media coverage (e.g., Financial Times, El País)
Radio interviews (e.g., SWR 2, Ö1, FM4, NPO Radio 1)
WiMIR Mentoring since 2018
Queen Mary University of London since 2021
Allyship Co-Chair at CHI 2022 and CHI 2023
Many news platforms provides uses with recommendations for a personalized experience that fits their interests and needs. However, aside from the consumption of news articles and user loyalty, additional values are relevant that need to be integrated in news recommender systems.
FairRecKit is a web-based analysis software that supports researchers in performing, analyzing, and understanding recommendation computations. The idea behind FairRecKit is to facilitate the in-depth analysis of recommendation outcomes considering fairness aspects. With (nested) filters on user or item attributes, metrics can easily be compared across user and item subgroups.
The purpose of this project is to understand how current systems used to recommend music affect artists and to propose alternative solutions that could benefit the artists. The goal is to identify potential problems that affect artists, and to draw on the artists’ perspective about how future recommender systems could work.
The comprehensive evaluation of the performance of a system is a complex endeavor: many facets need to be considered in configuring an adequate and effective evaluation setting. A single evaluation method or measure is not able to evaluate all relevant aspects in a complex setting where a multitude of stakeholders are involved. Employing a multi-method evaluation, where multiple evaluation methods or measures are combined and integrated, allows for getting a richer picture and prevents blind spots in the evaluation outcome.