We are working with Dr Hywel Williams on an ESRC funded New and Emerging Forms of Data Policy Demonstrator Projects focusing on the use of social sensing data to understand the health and wellbeing impacts from pollen and air pollution. Hywel is searching for a Post-doc with a PhD in computer science or a related quantitative discipline with knowledge of machine learning, scientific computing, and social media analysis to work on the project with us. More details below and see University of Exeter job site.
This ESRC-funded data science project will explore “social sensing” for tracking air pollution and airborne pollen. Pollen and pollution can have significant impacts on health and wellbeing; for example, people with hay fever may also suffer from asthma, with complications sometimes leading to hospitalisation. However, most cases are not severe enough to require formal medical treatment and therefore do not get recorded. This masks the true extent of these health conditions and their impacts on quality of life, making them hard to study and to manage. Meanwhile, the rise in web technologies and social media usage has created high-volume datasets that carry rich signals about a variety of social and environmental events. Analysis of such data can help improve knowledge of the health and wellbeing impacts of hayfever and asthma, particularly in conjunction with environmental and meteorological data.
We have pioneered a social sensing methodology that uses social media data to detect and locate environmental hazards. The methodology involves several stages: data harvesting, data cleaning (e.g. filtering for relevance and removing spam accounts), event detection, content analysis and data visualisation. The Postdoctoral Research Fellow will help to develop a social sensing prototype focused on pollen, air pollution, asthma and hay fever. The prototype will be evaluated for use by several partner organisations working on environment and public health issues: Met Office, Public Health England and AsthmaUK. The research fellow role will involve several tasks: utilise and improve existing methods for collecting social media data from popular platforms (Twitter, Instagram); utilise and improve existing geo-inference techniques that locate social media content without replying on embedded geo-tags or GPS coordinates; develop content classifiers to remove irrelevant content; and develop visualisation tools to make results easily available to users. Social sensing outputs will be analysed alongside health and environmental data to identify statistical patterns and relationships.
Applicants should possess a PhD in computer science or a related quantitative discipline and be able to demonstrate knowledge of machine learning, scientific computing, and social media analysis. The successful applicant will be able to present information on research progress and outcomes, communicate complex information orally and in writing, and prepare research outputs for publication.
For further information please contact Dr Hywel Williams, e-mail email@example.com or telephone (01392 723777).
To view the Job Description and Person Specification document please click here.