We use reinforcement learning and user modelling to develop practical systems that help users navigate massive data sets interactively. The research interests of the group include personalisation, exploratory search, experimental design and evaluation methodology. Our research is published in top venues for information retrieval and human-computer interaction. We are part of the Department of Computer Science at the University of Helsinki.
Representative publications:
Towards fine-grained adaptation of exploration/exploitation in information retrieval IUI 2017
Is exploratory search different? A comparison of information search behavior for exploratory and lookup tasks JASIST 2016
Balancing exploration and exploitation: Empirical parameterization of exploratory search systems CIKM 2015
Directing exploratory search: Reinforcement learning from user interactions with keywords IUI 2013
Alan and Dorota were invited to give a seminar talk called Manuscripts and newspapers: Using machine learning to map the sciences and identify political bias at the Helsinki Centre for Digital Humanities (HELDIG) pizza seminar.
Dorota gave a tutorial on Bandit Algorithms in Recommender Systems at RecSys 2019 in Copenhagen, Denmark.
Arlene presented A Framework for Annotating ‘Related Works’ to Support Feedback to Novice Writers at LAW13 in Florence, Italy.
Arlene presented Can Models of Author Intention Support Quality Assessment of Content? at BIRNDL in Paris, France.
Paper accepted at RANLP 2019 (Recent Advances in Natural Language Processing, 2019)!
Group Leader
Assistant Professor
Co-group Leader
Post-doctoral researcher
PhD student (University of Edinburgh)
Research assistant
jing.li@helsinki.fi
Research assistant
yang.liu@helsinki.fi
Research assistant
yu.an@helsinki.fi