Abstract
Allergic rhinitis (hayfever) affects a large proportion of the population in the United Kingdom. Although relatively easily treated with medication, symptoms nonetheless have a substantial adverse effect on wellbeing during the summer pollen season. Provision of accurate pollen forecasts can help sufferers to manage their condition and minimise adverse effects. Current pollen forecasts in the UK are based on a sparse network of pollen monitoring stations. Here, we explore the use of “social sensing” (analysis of unsolicited social media content) as an alternative source of pollen and hayfever observations. We use data from the Twitter platform to generate a dynamic spatial map of pollen levels based on user reports of hayfever symptoms. We show that social sensing alone creates a spatiotemporal pollen measurement with remarkable similarity to measurements taken from the established physical pollen monitoring network. This demonstrates that social sensing of pollen can be accurate, relative to current methods, and suggests a variety of future applications of this method to help hayfever sufferers manage their condition.
Highlights
Allergic rhinitis is an unpleasant disease which affects one in five 16–44 year olds, and up to 35% of 13–14 year olds in the UK [1,2]
We explore the utility of ‘social sensing’, systematic analysis of social media data, to track pollen and hayfever symptoms
Given that the number of pollen- and hayfever-related tweets is strongly correlated with the observed pollen count at each station, we can try to use the number of tweets to help predict pollen counts in areas without pollen observation stations
Summary
Allergic rhinitis (hayfever) is an unpleasant disease which affects one in five 16–44 year olds, and up to 35% of 13–14 year olds in the UK [1,2]. Many citizen science and crowdsourcing efforts rely on solicited observations, e.g., the UK Met Office ‘Weather Observation Website’ [13] or the UKSnowMap [14] that uses a particular hashtag (#uksnow) to allow users to report snowfall observations via Twitter The benefit of these efforts is that mostly reliable data, from dedicated volunteers, is collected through a structured interface. Social sensing is a form of unsolicited crowdsourcing which collects observations from social media These may be relevant and useful to forecasters but are not produced for this purpose and unlikely to follow a consistent reporting structure. The final part of the analysis will examine the performance of simple linear regression models that predict pollen count as a function of social sensing observations If such models are shown to be effective, they might be useful for providing estimated pollen counts in areas where there is no monitoring station or in the case of monitoring station failure. The manuscript is structured as follows: Section 2 describes the datasets and methods used; Section 3 describes the empirical results and gives some interpretation; Section 4 tests the performance of simple predictive models; and Section 5 summarises the main conclusions from the work
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
