Research project

SafeSpacesNLP

Research groups:

Agents, Interaction and Complexity
Lead researchers:

Dr Stuart Middleton
Research funder:

EPSRC
Website:

https://www.tas.ac.uk/safespacesnlp/
Status:

Not active

Project overview

We will explore the use of Socio-Technical Natural Language Processing (NLP) for classifying behavioural online harms within online forum posts (e.g. bullying; drugs & alcohol abuse; gendered harassment; self-harm), especially for young people. Our socio-technical AI will explore both zero-shot and graph-based NLP algorithms for behaviour classification, using a cyclic socio-technical methodology. This approach will facilitate incremental use of human feedback for iterative learning and re-ranking, overcoming the limited training data issue and keeping a 'human in the loop'. We follow an inclusive multi-disciplinary research approach, integrating stakeholders into our experiments from the start.

Staff

Lead 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

Collaborating research institutes, centres and groups

Agents, Interaction and Complexity

We research the science and engineering of complex areas. We focus on areas including human-machine teams and human-in-the-loop interaction.

Research outputs

Trust, regulation, and human-in-the-loop AI: within the European region

Stuart Middleton, Emmanuel Letouzé, Ali Hossaini & Age Chapman, 2022, Communications of the ACM, 65(4), 64–68

DOI: 10.1145/3511597

Type: article