Pilot Projects

Survey form being filled out

Automating Question Capture

Building high quality question banks will encourage reuse of questions and data, and transparency of research. This ESRC funded project seeks to utlise machine learning technologies to capture the content from existing questionnaires, reducing manual extry and increasing quality ... read more

Pile of Lego bricks

Predicting concepts from question text

This UCL funded project will take the outputs from the automation of question capture project and auto-tag with concepts which align with the European Language Social Science Thesaurus (ELSST) ... read more


The Team

Bringing together expertise in data management, metadata and machine learning

  • Suparna De - University of Surrey (Co-Investigator)
  • Sanaz Jabbari - UCL, RITS (Developer)
  • Jon Johnson - UCL, CLOSER (Co-Investigator)
  • Jenny Li - UCL, CLOSER (Data Management)
  • Harry Moss - UCL, RITS (Developer)

The Advisory Board

Providing expert advice to the project

  • Ciara Cummins (Central Statistical Office, Ireland)
  • Neil Fitzgerald (British Library)
  • Deirdre Lungley (UK Data Archive)
  • Klaus Moessner (Technical University Chemnitz & University of Surrey)
  • Carsten Thiel (Consortium of European Social Science Data Archives)
  • Wei Wang (Xian Jiatong Liverpool University)
  • Jeremy Yates (UCL)