en
Technical report
Open access
English

Extracting localized information from a Twitter corpus for flood prevention

Publication date2019
Abstract

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 quality and precision 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.

Citation (ISO format)
BRANGBOUR, Etienne Alaric et al. Extracting localized information from a Twitter corpus for flood prevention. 2019
Main files (1)
Report
accessLevelPublic
Identifiers
  • PID : unige:129068
222views
75downloads

Technical informations

Creation01/17/2020 5:12:00 PM
First validation01/17/2020 5:12:00 PM
Update time03/15/2023 6:47:31 PM
Status update03/15/2023 6:47:30 PM
Last indexation01/17/2024 8:49:19 AM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack