Social Media for Weather Impacts
We're a research group at McGill University working to make social media data more useful to crisis managers.
Social media can generate a wealth of real-time information during crisis events. However, large volumes of data and irrelevant content create practical challenges.
We're building a suite of deep learning models to classify Tweets during extreme weather events to turn unstructured social media data into actionable insights.
We published a journal article "Using deep learning and social network analysis to understand and manage extreme flooding."
This work was featured in a recent press release
and featured in various news articles.
Reports
Weather news accounts
Data
- Weather news accounts: weather-news-accounts.csv
- Twitter accounts from the National Weather Service: nws-accounts.txt
- Popular (non-governmental and non-commercial) Twitter accounts: personal-accounts.txt
- Popular commercial accounts: commercial-accounts.txt
Codebase
Publications/ presentations
Present
Social media can generate a wealth of real-time information during crisis events. However, large volumes of data and irrelevant content create practical challenges.
We're building a suite of deep learning models to classify Tweets during extreme weather events to turn unstructured social media data into actionable insights.
We published a journal article "Using deep learning and social network analysis to understand and manage extreme flooding." This work was featured in a recent press release and featured in various news articles.
Reports
Data
- Weather news accounts: weather-news-accounts.csv
- Twitter accounts from the National Weather Service: nws-accounts.txt
- Popular (non-governmental and non-commercial) Twitter accounts: personal-accounts.txt
- Popular commercial accounts: commercial-accounts.txt