Extracting localized information from a Twitter corpus for flood prevention

03/12/2019

∙

by   Etienne Brangbour, et al.

∙

0

∙

share

In this paper, we discuss the collection of a corpus associated to tropical storm Harvey, as well as its analysis from both spatial and topical perspectives. From the spatial perspective, our goal here is to get a first estimation of the granularity and reliability of the geographical information featured in the collected corpus. From a topical perspective, we discuss the representation of Twitter posts, and strategies to process an initially unlabeled corpus of tweets.