The Twitter Anemometer

hubie writes:

Wind speed is something that is hard to qualitatively describe from person to person. One person's playful breeze is another's biting annoyance. For a very long time this was a problem in the maritime domain so a couple of centuries ago Francis Beaufort came up with the Beaufort Scale. This scale ties wind speed to objective observations. It was first applied to sea state, but it was later extended for observations on land.

There is a research field growing up around the idea of "social sensing", where social media platforms, particularly Twitter, can be used for real-time detection and tracking of natural events, such as earthquakes, forest fires, air quality, etc. A group of researchers from the University of Exeter have established a social Beaufort scale using Twitter. They looked at 110k weather-related tweets in the UK spanning two years to see if they could detect wind-related effects and estimate the wind magnitudes by looking at the language and emojis used, similar to what is done with the Beaufort scale (well, except for the emojis). They found that a simple text classifier can be used to detect high-wind events fairly accurately and the severity of these events can be inferred by considering the tweet volume.

Journal Reference:
Iain S. Weaver, Hywel T. P. Williams, Rudy Arthur. A social Beaufort scale to detect high winds using language in social media posts [open], Scientific Reports (DOI: 10.1038/s41598-021-82808-x)

ABSTRACT:

Read more of this story at SoylentNews.