Information Retrieval Lab

The Information Retrieval Lab is a team of faculty, research scientists, programmers and students who work together on models and algorithms that allow computers to process and make inferences about human language text. Our work is in the areas of information retrieval, data mining and applied machine learning (mainly for web data), with applications to search engines, recommender systems, plagiarism detection, opinion/sentiment mining, and text analytics, and with particular emphasis to large-scale web data.

The Information Retrieval Lab is affiliated with the Department of Computer Science (DIKU), of the University of Copenhagen.

Information Retrieval (IR)

Crawling, indexing and ranking models, large scale Web search optimisation, domain-specific IR.

Computational Linguistics

Syntactic, semantic and discourse text processing for web search and analytics.

Educational Data Mining

Applications in online course optimization, curriculum creation, and teaching personalization.

Learning to Rank

Dynamic online ranking evaluation for web search using online learning from machine learning.

Web Science

Emerging challenges in web-mediated data exchange, such as social media platforms and archiving initiatives.

Deep Learning for Text

Recurrent neural networks for text understanding and retrieval.


Computational epidemiology based on web-mined data, infectious disease surveillance, and vaccine effectiveness.

Text Analytics

Topic, aspect and trend mining from large scale unstructured text using statistical and linguistic analysis.

Formal IR and Interaction

Non-classical mathematics for models of information seeking, retrieval and interaction.