About the Project
Number of awards
Start date and duration
September 2021 for 3 years full time.
We are seeking a highly motivated PhD student to establish an evidence-based framework for an optimal natural language processing (NLP) solution (including a working prototype) to support public health evidence extraction and synthesis research activity. The student will be based in the NIHR Innovation Observatory at Newcastle University, but work collaboratively across the School of Computing and the Population Health Sciences Institute (PHSI). PHSI is the academic home of the Innovation Observatory.
Public health evidence is being produced and published at an unprecedented rate and scale. This evidence can take many forms; for example, the more common and conventional types and sources of published evidence include journal articles, conference abstracts/proceedings, technical reports, and clinical trial records/registries. However, to keep pace with the rapidly evolving public health landscape, and to respond to the critical needs, issues, and public health crises of today in a timely manner, there is a growing need to explore, leverage and integrate insights from more novel sources of evidence (e.g., soft-intelligence), including social media and news article data. A common thread across all this evidence is that such data is, at large, stored in a noisy, unstructured format, which makes secondary research-led activities in data extraction, synthesis, and reporting incredibly challenging.
The latest innovations in artificial intelligence (AI), machine learning, and NLP tools and techniques offer the ability to rapidly extract, analyse, synthesise, and understand unstructured textual data, at scale. Recent breakthroughs in these technologies have led to vastly improved NLP models, which are able to capture and model more complex linguistic relationships than ever before. By providing the ability to assess and analyse large quantities of this data, NLP has opened up vast opportunities for public health evidence synthesis research to support evidence-informed decision making at both local and national levels.
Broadly, the aim of this research project will be to establish an evidence-based framework for an optimal NLP solution (including a working prototype) to support public health evidence extraction and synthesis research activity. Working closely with their supervisory team, the successful candidate will carefully design and deliver a programme of work to:
- Rigorously scope and map existing NLP tools, pipelines, and technologies
- Critically assess candidate tools based on their suitability in the context of automated public health evidence extraction and synthesis, using multi-criteria decision-making and benchmarking methods
- Classify, compare, and contrast statistics-driven vector space machine learning models with deep learning approaches for NLP in this setting
- Establish a baseline for relevant required features and performance to generate an initial evaluation framework for an optimal NLP solution
- Conduct a ‘compatibility study’ to investigate how combinations of different NLP tools and packages can operate together
- Develop a refined version of the evaluation framework, and validate the framework against a working prototype for an optimal NLP tool/pipeline.
Name of supervisor(s)
Dr Christopher Marshall, Dr Amir Atapour-Abarghouei, Professor Dawn Craig.
The successful applicant will have, or expect to obtain an upper second class or above in Computer Science and have a strong interest in (and working knowledge of) secondary public health research methods (e.g, evidence synthesis, systematic reviewing etc.). Alternatively, candidates (Masters degree (Merit or above) from a public health background who can demonstrate exceptional interest, enhusiasm and experience in AI, machine learning, and NLP will also be considered. If your first language is not English you need an overall IELTS score of 6.5 (at least 5.5 in all sub-skills) or equivalent language qualification. Non-UK candidates must contact [Email Address Removed] regarding eligibility and fees.
How to apply
You must apply through the University’s online postgraduate application system by creating an account. To do this please select ‘How to Apply’ and choose the ‘Apply now’ button.
All relevant fields should be completed, but fields marked with a red asterisk must be completed. The following information will help us to process your application. You should:
- click on programme of study
- insert 8300F in the programme code section and click search
- select Programme name ‘PhD in the Faculty of Medical Sciences (full time) – Health Services Research’
- insert PH026 in the studentship/partnership reference field
- attach a covering letter and CV. The covering letter must state the title of the studentship. Please quote reference code PH026 and state in the covering letter how your interests and experience relate to the proposed project
- attach degree transcripts* and certificates and, if English is not your first language, a copy of your English language qualification.
*You will not be able to submit your application until you have submitted your degree transcript/s.
Based on your current searches we recommend the following search filters.
Based on your current search criteria we thought you might be interested in these.