Text Mining and Retrieval Leiden (TMRL) focusses on text mining and retrieval problems in complex domains.

The archaeology domain produces large amounts of texts, too much to effectively read or manually search through for research. To alleviate this problem, we created a search system (called AGNES), which combines full text search with entity and geographical search.

Patients share valuable advice and experiences with their peers in online patient discussion groups.

Promotor: J.N. Kok, Co-Promotor: A.J. Knobbe

Promotor: J.N. Kok, Co-promotor: C.M. Soares, A.J. Knobbe

An effective and equitable approach to resource conflicts?

Modern computer-aided simulation tools used by various industries produce gigabytes of data. But currently, they take days and even up to weeks of computation effort. To make the best use of all these data, the DAMIOSO project focuses on developing algorithms and tools for managing, mining, and optimizing…

Collecting data in sports increased in importance the last few years.

This project develops a scientific method to extract clinically relevant new information from patient forum websites that discuss patient experiences concerning e.g. medication, nutrition, co-morbidities, genetic factors etc.

This thesis applies data mining in commercial settings in the telecommunications industry.

The elicitation of mentor teachers' practical knowledge by prospective teachers

Due to the modern techniques of combinatorial chemistry and high-throughput screening, data on the biological activity of many millions of compounds is known. However, it is still very difficult to transfer this data into knowledge: if we know that compounds A and B bind to a certain protein with high…

Promotor: Prof.dr. J.N. Kok, Co-Promotor: W.A. Kosters

PUMA aims at composing a geological map of the urban mine of Amsterdam for a selection of metals. Where are main deposits of copper, iron and aluminium located, when will they become available for secondary production, in what state and shape are they?

The change from a closed institution to an open living environment for patients with late stages of dementia will give the patients more freedom in their day-to-day life. The effect of this change on the patients’ mobility, activity and interaction with others will be assessed with sensor technology…

Promotor: Prof.dr. J.N. Kok, Co-promotor: Dr. A.J. Knobbe

In this thesis we explore machine and deep learning approaches that address keychallenges in high dimensional problem areas and also in improving accuracy in wellknown problems. In high dimensional contexts, we have focused on computational fluid dynamics (CFD) simulations.

On dinsdag 26 juni 2018, Linlin Sun defended her doctoral thesis ‘International Environmental Obligations and Liabilities in Deep Seabed Mining’. The doctoral research was supervised by Prof. dr. N.J. Schrijver en Prof. dr. E.C.P.D.C. De Brabandere.

Mining time series is a machine learning subfield that focuses on a particular data structure, where variables are measured over (short or long) periods of time.

Abdolreza Alamdar Baghini defended his thesis on 5 December 2019.

We will use Artificial Intelligence to make an intelligent, multilingual search engine for archaeological texts, which will enable new discoveries about the human past.

Latest technological developments in data mining and profiling.

Open Educational Resources (OER) have the potential to change teaching in Higher Education, but adoption is low despite the growing amount of resources available. The current project aims to investigate if and how teacher communities can foster adoption of OER in curricula.

The Digital Archaeology research group manages two computer laboratories with different purposes: the teaching lab (F1.01) and the research lab (A1.13a).

With the rise of information and communication technologies, large amounts of data are being generated and stored in databases. In order to get a better grip on these large amounts of data, serious efforts are being made to discover patterns and relations in the data with the help of new techniques.…

Policy Note Insecurity in Burkina Faso – beyond conflict minerals: The complex links between artisanal gold mining and violence

Detecting planets during their formation stages is crucial for understanding the history and diversity of fully developed planetary systems like our own. However, observing young planets directly is challenging because they are often deeply embedded within their host protoplanetary discs, rich in gas…

PhD defence

Source: J Cheminform, Volume 6, Issue 1 (2014)

Data and information should be stored in a way that computers can understand, says Barend Mons, professor of Biosemantics at the Leiden University Medical Center and Chair of the High Level Expert Group for the European Open Science Cloud. We speak with him about FAIR data, knowlets and nanopublicat…

The majority of scientists, from archaeologists through to zoologists, collect enormous volumes of data. Their massive databases contain large amounts of information which is difficult for humans to filter. With a solid grounding in statistics and computer science, we can develop algorithms for analyzing…

The majority of scientists, from archaeologists through to zoologists, collect huge volumes of data. Their massive databases contain large amounts of information which is difficult for humans to filter. With a solid grounding in statistics, we can develop algorithms for analysing and identifying patterns…

This dissertation focuses on the question how text and paratext contribute to the way that text in a network-like environment is clearly bordered and at the same time can easily be linked to other texts.

Learn more about the minor Digital Humanities and Artificial Intelligence.

We hold the annual Digital Humanities Pilot Project Symposium and Digital Skills Winter Workshop Week in the last week of January. It is open to all LU staff and PhD/MA students.

Several so-called Special Interest Groups are linked to DSRP. These groups focus on specialized topics and organize their own group meetings, talks etc. Contact the group leader if you are interested to join. It is possible to be a member of multiple groups.

Promotor: J.N. Kok, Co-promotor: W.A. Kosters

With textnets it is possible to visualize and analyze textual data in novel ways.

Recontextualising the Papyri from Roman Soknopaiou Nesos / Dimê (Fayyum, Egypt)

This book is the first grammar on Ternate Malay, a local variety of Malay spoken on the island of Ternate, North-Moluccas, Indonesia.

The SAPPAO project aims to optimise the accuracy and reliability of predicting scheduled flight times. The full name of the project is 'A Systems Approach towards Data Mining and Prediction in Airlines Operations'.

Data science offers great opportunities for legal research, according to Simone van der Hof and Bart Custers (eLaw). But at the same time, we have to keep an eye on the unwanted side effects of big data - such as ethnic profiling.

Computational linguistics uses computational methods to help answer linguistics questions across a variety of topics.

In this theme you will be supplied with a firm background in the core of current computational linguistics and a solid comprehension of its neighboring fields.

An incredible quantity of archaeological reports are stored in digital archives. If you want to search for information in them, you have to do this manually. And that is a real chore. Archaeologist Alex Brandsen has now used deep learning, a form of artificial intelligence, to develop a search engine…