Identification of depression and loneliness in early stages of dementia

These projects are open to students worldwide, but have no funding attached. Therefore, the successful applicant will be expected to fund tuition fees at the relevant level (home or international) and any applicable additional research costs. Please consider this before applying. 

This is a project of an interdisciplinary nature, where the PhD candidate will endeavour to use sentiment and emotion analysis to classify text. It has been demonstrated that word use is a reliable indicator of a person’s psychological state. Thus, this project will attempt to identify depression and loneliness in people diagnosed with early stages of dementia.

The people who are being newly diagnosed with dementia are likely to be digitally literate, using technology at work and home. A recent survey found that 82% of people with dementia used mobile phones to connect with others and 23% used personal assistants such as Alexa and Siri. By focusing on people with dementia under 70 years, this project will create an adaptive and relevant solution for the future. The resulting technology has the potential to impact the lives of hundreds of thousands of people. In the UK, it is projected that by 2050, 1.6 million people will be living with dementia. If a third of these people benefit from this intervention, that would represent over 200,000 people in the UK.

People with dementia are at increased risk of depression and loneliness compared to the general population. Both, depression and loneliness have wide ranging detrimental effects from increased risk of physical health conditions to negative impact on cognition. Depression and loneliness are also associated with an increased all-cause mortality.

After receiving ethical approval, the PhD candidate will be expected to participate in (and to some extent organise) the annotation of free text provided by different people (some of them diagnosed with dementia). The annotation will be carried out to acquire sufficient training data for further analysis. Several NLP algorithms will then be tested to create a supervised machine learning classifier to identify specific sets of emotions. We have already experimented with this in previous work, but further research should be undertaken to fully support the identification of depression and loneliness.

Essential Background:

Decisions will be based on academic merit. The successful applicant should have, or expect to obtain, a UK Honours Degree at 2.1 (or equivalent) in a relevant subject (computer science, mathematics, or physics) is desirable, though candidates with degrees on different subjects but sufficient experience and interest in the topic are encouraged to apply. Programming experience on a high-level, object-oriented, programming language is also desirable..

Application Procedure:

Formal applications can be completed online: https://www.abdn.ac.uk/pgap/login.php.

You should apply for Computing Science (PhD) to ensure your application is passed to the correct team for processing.

Please clearly note the name of the lead supervisor and project title on the application form. If you do not include these details, it may not be considered for the studentship.

Your application must include: A personal statement, an up-to-date copy of your academic CV, and clear copies of your educational certificates and transcripts and 2 academic references (but those who have been out of education for more than three years may submit one academic and one professional reference).

Please note: you DO NOT need to provide a research proposal with this application.

If you require any additional assistance in submitting your application or have any queries about the application process, please don't hesitate to contact us at pgrs-admissions@abdn.ac.uk