SafeSpacesNLP: Behaviour classification NLP in a socio-technical AI setting for online harmful behaviours for children and young people

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

ConversationMoC: encoding conversational dynamics using multiplex network for identifying moment of change in mood and mental health classification

Loitongbam Gyanendro Singh, Stuart E. Middleton, Tayyaba Azim, Elena Nichele, Pinyi Lyu & Santiago De Ossorno Garcia, 2024

Type: conference

Implementing responsible innovation: the role of the Meso-level(s) between project and organisation

Bernd Carsten Stahl, Virginia Portillo, Hanne Wagner, Peter J. Craigon, Dimitrios Darzentas, Santiago De Ossorno Garcia, Liz Dowthwaite, Chris Greenhalgh, Stuart E. Middleton, Elena Nichele, Christian Wagner & Helena Webb, 2024, Journal of Responsible Innovation, 11(1)

DOI: 10.1080/23299460.2024.2370934

Type: article

On the legal aspects of responsible AI: adaptive change, human oversight, and societal outcomes

Daria Onitiu, Vahid Yazdanpanah, Adriane Chapman, Enrico Gerding, Stuart E. Middleton & Jennifer Williams, 2023

Type: conference

Identifying key challenges and needs in digital mental health moderation practices supporting users exhibiting risk behaviours to develop responsible AI tools

Elena Nichele, Anita Lavorgna & Stuart Middleton, 2022, SN Social Sciences, 2(10), 217

DOI: 10.1007/s43545-022-00532-3

Type: article

Detecting moments of change and suicidal risks in longitudinal user texts using multi-task learning

Tayyaba Azim, Gyanendro Singh Loitongbam & Stuart Middleton, 2022

DOI: https://aclanthology.org/2022.clpsych-1.19/