View all research projects
Research project

Gendered body language and speech styles in UK Parliament using machine learning

Project overview

This project aimed at studying how gender mediate body language and speech styles in Parliamentary debates, using methodological and empirical contributions to both fields. We developed tools to study audio in Parliamentary debates from the House of Commons and used methods from Natural Language Technique to extract information from Hansard transcripts.

Staff

Lead researchers

Dr Rafael Mestre PhD, MSc, BSc

Lecturer
Research interests
  • Responsible Research and Innovation of emergent technologies
  • Multimodal machine learning and Natural Language Processing
  • Computational social science
Connect with Rafael

Email: R.Mestre@soton.ac.uk

Dr Jessica Smith

Lecturer in Politics & International Rel
Research interests
  • Political behaviour and gender-based stereotyping
  • Executive politics
  • British politics
Connect with Jessica

Email: J.C.Smith@soton.ac.uk

Other researchers

Dr Stuart Middleton

Associate Professor
Research interests
  • Natural Language Processing
  • Human-in-the-loop NLP: Active Learning, Adversarial Training, Rationale-based Learning, Interactive Sense Making
  • Information Extraction: Few/Zero Shot Learning, Graph-based Models, Behaviour Classification, Geoparsing/Location Extraction, Event Extraction, Argument Mining
Connect with Stuart

Email: sem03@soton.ac.uk

Professor Matt Ryan

Professor
Research interests
  • Democracy
  • Social Research Methods
  • Web Science
Connect with Matt

Email: M.G.Ryan@soton.ac.uk

Professor Tim Norman

Head of School
Research interests
  • Learning and reasoning under uncertainty
  • AI safety
  • Human-AI collaboration
Connect with Tim

Email: T.J.Norman@soton.ac.uk

Research outputs