Computing flood probabilities using Twitter: application to the Houston urban area during Harvey

12/07/2020
by   Etienne Brangbour, et al.
0

In this paper, we investigate the conversion of a Twitter corpus into geo-referenced raster cells holding the probability of the associated geographical areas of being flooded. We describe a baseline approach that combines a density ratio function, aggregation using a spatio-temporal Gaussian kernel function, and TFIDF textual features. The features are transformed to probabilities using a logistic regression model. The described method is evaluated on a corpus collected after the floods that followed Hurricane Harvey in the Houston urban area in August-September 2017. The baseline reaches a F1 score of 68 results.

READ FULL TEXT
research
06/25/2023

Stance Prediction and Analysis of Twitter data : A case study of Ghana 2020 Presidential Elections

On December 7, 2020, Ghanaians participated in the polls to determine th...
research
12/24/2016

KS_JU@DPIL-FIRE2016:Detecting Paraphrases in Indian Languages Using Multinomial Logistic Regression Model

In this work, we describe a system that detects paraphrases in Indian La...
research
03/12/2019

Extracting localized information from a Twitter corpus for flood prevention

In this paper, we discuss the collection of a corpus associated to tropi...
research
11/30/2020

Flood Detection via Twitter Streams using Textual and Visual Features

The paper presents our proposed solutions for the MediaEval 2020 Flood-R...
research
11/16/2015

Learning about Spanish dialects through Twitter

This paper maps the large-scale variation of the Spanish language by emp...
research
02/06/2023

Baseline Method for the Sport Task of MediaEval 2022 with 3D CNNs using Attention Mechanisms

This paper presents the baseline method proposed for the Sports Video ta...

Please sign up or login with your details

Forgot password? Click here to reset