University at Buffalo (UB) researchers are examining how weather-related tweets can be analyzed to improve computer models that recommend safe driving speeds and which roads motorists should avoid during inclement weather.
"Twitter users provide an unparalleled amount of hyperlocal data that we can use to improve our ability to direct traffic during snowstorms and adverse weather," says lead study author Adel Sadek, director of UB's Institute for Sustainable Transportation and Logistics.
Traffic planners rely on models that analyze vehicular data from cameras and sensors, as well as weather data from nearby weather stations. However, the accuracy of those methods is limited because traffic and weather observations do not provide information on road surface conditions. Twitter can help address this limitation because users often tweet about weather and road surface conditions, and many choose to share their location via global-positioning systems.
The UB study examined more than 360,000 tweets in the Buffalo Niagara region from 19 days in December 2013. The researchers identified about 3,000 relevant tweets by tagging keywords such as "snow" and "melt." They then refined the data via Twitter Weather Event Observation, inserted the data into a model containing traffic and weather information, and found it improved the accuracy of existing models.
From University at Buffalo News
View Full Article
Abstracts Copyright © 2015 Information Inc., Bethesda, Maryland, USA