Applying Natural Language Processing (NLP)
to real-world problems

Welcome to the Text Analysis Group (TAG) Laboratory at the University of Sussex. The laboratory is
part of a long line of AI research at Sussex, starting in the 1960s. We conduct research in NLP, the
analysis of text and language by computers, and apply these technologies to the interpretation of text
documents, social media and other communications, working with business, government and others.

  • Lorem
  • Ipsum
  • Dolor

What we do

Our basic research is in the field of distributional semantics, which captures the meaning of words or phrases in terms of the contexts in which they occur. We have developed our own approach, using data structures called APTs. Details are available here.

Our applied research looks at the application of NLP to the processing of large volumes of text documents. We have developed approaches to classification (including sentiment and attitudinal analysis), information extraction, influencer analysis, automatic tagging and automated dialogue. Much of our work is implemented in the Method52 framework (see image, left), details of which can be found here.

Who we are

The TAG laboratory was co-founded by Professor David Weir and Dr Jeremy Reffin. We have a team of 11 research associates, who are also undertaking PhDs, working alongside 4 faculty and research fellows. See here for further details.

We also co-founded the Centre for Analysis of Social Media (CASM), and our CASM work is conducted alongside colleagues based at the think tank Demos. See here for further details of the work and the CASM team members at Demos.

Who we work with

We work with academics and organisations to study the impact of social media on politics, policy-making and law enforcement, and to investigate associated emerging social phenomena including radicalisation, community intolerance, information spread and coordination (e.g. in disaster response), and approaches to health and wellbeing. See here for further details of relevant work.

We also work with companies that need to interpret large volumes of text documents, social-media messages and other forms of natural-language communication. We offer both consulting and software development services in these areas. See here for further details.

Key Activities and collaborations

We have worked with more than 20 organisations over the past 6 years on a wide range of challenges.

  • Centre for Analysis of Social Media

    CASM is a collaboration between the TAG Laboratory and the think-tank Demos. We investigate the impact of social media and of associated social phenomena.

  • Method52

    Method52 is a software platform for the analysis of unstructured text that we co-develop and use to undertake much of our applied research. It is also deployed commercially.

  • Sussex Humanities Lab

    Members of the TAG Laboratory are part of the Sussex Humanities Lab, which is dedicated to developing and expanding research into how digital technologies are shaping our culture and society.

  • CASM Consulting LLP

    Much of our applied consulting work is conducted through our associated consulting practice, CASM Consulting LLP. In addition to providing research and consulting services, the company develops commercial-grade technology in Natural Language Processing (NLP) and social media analysis.

  • Distributional Semantics

    In our research we have developed a new approach for composing word meanings into phrase and sentence meanings. A word, phrase or sentence meaning can be represented as a single data structure called an APT; its meaning is then interpretable from the perspective of each word in the phrase or sentence.

  • Policing Hate Crime

    This project explores ways to improve our understanding of hate crime and other community-related incidents. It is a collaborative project with the Metropolitan Police Service, Palantir Technologies, Demos and CASM Consulting, and is funded by the Police Knowledge Fund.

  • Near You Now Demonstrator

    The Near You Now Demonstrator enables users to access local news stories on mobile devices based on relevance at their precise location. This was a joint research project with Near You Now Ltd, Archant Community Media Ltd, KentishTowner and Streetlife.com, and was funded by Innovate UK.

  • In the Hands of the Analyst

    This project explored the approaches required to undertake attitudinal analysis using social media data in a principled fashion, taking into account issues around representitivity, the limits of current technology and ethical considerations. This was a joint research project with Ipsos MORI, Demos, and CASM Consulting LLP, and was funded by the Innovate UK, the ESRC, the EPSRC and DSTL.

Contact Us

Please get in contact with us to hear more about our work or if you have a challenge in text analysis that you would like us to tackle.

David Weir
Professor of Computer Science
Department of Informatics
University of Sussex
Brighton, BN1, 9QJ
East Sussex, UK

Office: Chichester-1 213
Tel: +44 (0)1273 678993