About B-TXT

B-TXT, the Brussels Digital Text Lab, is a VUB core facility for researchers working with textual data. We combine approachable methodological guidance with technical expertise, reusable resources, and tailored solutions for larger research projects.

Our Core Philosophy

Five commitments guide how B-TXT supports research.

Innovative

Promote high-quality, reproducible, and innovative research.

At Scale

Advocate for responsible use of computational and financial resources.

Safe

Facilitate safe storage and processing of sensitive research data.

Inclusive

Support all VUB researchers with our services.

Connected

Connect researchers working on NLP and digital humanities within and outside the VUB.

Who B-TXT Supports

Our support is shaped by your affiliation, the scale of the question, and the kind of collaboration you need.

VUB master’s students

Master’s students can ask quick questions during our Thursday open office hours. For an official one-hour appointment with methodological feedback, a supervisor can book on their behalf.

VUB researchers

Our services are available to VUB researchers across career stages, departments, and disciplinary backgrounds.

VUB research groups

Research groups can request tailored presentations, workshops, or custom code. This work is paid, with discounts possible when advice, software, or datasets can be reused by other researchers.

Researchers outside VUB

External researchers and other third parties can book one free one-hour consultation per project. Further support follows a separate pricing scheme.

Our Expertise

Explore the areas where we can help. Expand a topic for a brief overview.

Digitisation of handwritten or printed text

We help turn handwritten historical documents and printed books into digital text, recommend suitable digitisation software, and lend a scan tent or portable document scanner for archival work.

Searching text

We help make document collections searchable for words, linguistic structures, and more abstract concepts.

Distant reading

We support large-scale exploration of collections such as news, social media, corpora, historical datasets, and novels. Methods include topic detection, hate-speech flagging, sentiment analysis, genre detection, tracing language shifts, and clustering texts by similarity.

Web scraping

We help collect online textual material and turn it into a clean, structured, and searchable corpus.

Data cleaning and conversion

We help correct transcribed text, structure source material as searchable corpora, and prepare collections of PDFs or documents for publication, preservation, or enrichment.

Spatial analysis

We support researchers working with spatial data, including the creation of interactive maps.

Audio transcription

We help automate the secure transcription of interviews and other audiovisual material.

Annotation and tagging

We support workflows such as part-of-speech tagging, named entity recognition, and lemmatisation, as well as structured annotation for discourse analysis.

Interactive data visualisation

We create static visualisations for presentations and interactive visualisations, including digital storytelling, to help researchers communicate their results.

Our Team

Meet the people who provide B-TXT’s day-to-day support and help shape its scientific direction.

View the scientific board
  • Jolien GijbelsHistory
  • Tom VerthéPolitical science
  • Laura RosseelLinguistics
  • Bob PierikHistory, Digital humanities
  • Eva Ulrike PirkerLiterary studies
  • Ward PoelmansScientific Data and Compute, HPC
  • Free De BackerEducation
  • Paul Van EeckeAI and computational linguistics
  • Ann DoomsMathematics, AI and technical expertise