Data for Mining rainfall spatio-temporal patterns in Twitter : a temporal approach

This approach was evaluated by conducting a case study in the city of São Paulo, Brazil, using a dataset of rainfall data provided by the Brazilian National Disaster Monitoring and Early Warning Center. The results provided evidence that the rainfall gauge time-series and the rainfall-related tweets are not synchronized, but they are linked to a lag-time that ranges from −10 to +10 min. Furthermore, our temporal approach is thus able to pave the way for detecting patterns of rainfall in real-time based on social network messages.<br><br>AGILE 2017 dataset The AGILE 2017 is a raw dataset of rainfall gauges and tweets that are openly available in CSV format.

This dataset was published at the 20th AGILE Conference The dataset contains: rainfall_gauges.csv: The rainfall data collected from the National Center for Monitoring and Early Warning of Natural Disasters CEMADEN referring to the city of Sao Paulo, Brazil. The rainfall measurements were provided in linear depth (millimeters) and with two sizes of temporal window: 10 minutes when it was raining and 60 minutes otherwise. rainfall_gagues_removed.csv: The rainfall gauges removed due the lack of reliability. tweets.csv: The georeferenced tweets retrieved by Twitter Streaming API for the same period and administrative boundaries of rainfall data. tweets.ts.csv: The frequency of rainfall-related tweets and all tweets.