PhD in Longitudinal Natural Language Processing Methods with Applications to Mental Health
We are advertising a PhD position in the context of the Alan Turing Institute AI fellowship on “Creating time sensitive sensors from user-generated language and heterogeneous content”, led by Prof Maria Liakata. The Alan Turing Institute is the UK’s national Institute for data science and artificial intelligence. Prof Liakata’s AI fellowship is one of five prestigious such awards made in Autumn 2019 and funded by the UK Department of Business, Energy and Industrial Strategy (BEIS). Her fellowship aims to strengthen the nascent area of personalised longitudinal natural language processing (NLP) models from user-generated content (UGC). More information about the AI fellowship is available at: https://www.turing.ac.uk/people/researchers/ai-fellows
Overview The successful applicant will join Prof Liakata’s research team for a four-year PhD degree at the School of Electronic Engineering and Computer Science (EECS) at Queen Mary University of London (UK) and The Alan Turing Institute (London, UK). EECS is an exciting and dynamic environment with a reputation for excellence in both research and teaching. We are 11th in the UK for quality of computer science research (REF 2014) and 6th in the UK for quality of electronic engineering research (REF 2014). Our academics undertake world-leading research in a lively and supportive research community.
The PhD project will focus on the intersection of natural language processing (NLP), machine learning (ML) and mental health. The overall goal is to combine UGC from social media and smart devices in a longitudinal fashion, aiming at representing the user in a temporally sensitive way, with particular focus on capturing his/her mental health state over time. The successful applicant is expected to work on two or more of the following :
• Longitudinal dynamic representations of language and other UGC;
• Multi-scale methods for combining user-generated heterogeneous data at different temporal granularities;
• Methods for synthetic language generation from language and heterogeneous UGC;
• Methods for change point detection in language use and behaviour;
• Longitudinal predictions for condition change;
• An appropriate evaluation framework for each task;
• Methods for combining longitudinal evidence for condition change into interpretable summaries;
• Co-design of new instruments for assessing changes in mental health based on interpretable summaries and longitudinal patterns of change in heterogeneous language and UGC.
• Modeling ethical aspects of longitudinal language sensors.
Desired outputs include publications in top-tier NLP and ML venues and are expected to have high impact in the fields of NLP and mental health, both in terms of methodological innovation and their application to better understanding real-world mental health data. There will also be the opportunity to work closely with research engineers at the Alan Turing Institute and contribute to the creation of language sensors (software tools and libraries that incorporate personalised longitudinal language modeling methods).
For more details please see: tinyurl.com/rfconbe<https://t.co/zmzP6SALh1>
For queries regarding the PhD topic and project, please contact Prof Maria Liakata (mliakata at turing.ac.uk). For queries about the application process, refer to eecs-phd-enquiries at qmul.ac.uk .
Maria Liakata Turing Institute AI Fellow Professor in Natural Language Processing Cognitive Science Group School of Electronic Engineering and Computer Science Queen Mary University of London -------------------------------------- Department of Computer Science University of Warwick
-------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 15064 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20200415/09d64750/attachment.txt>