@inproceedings{hamoui-etal-2020-flodusta,
title = "{F}lo{D}us{TA}: Saudi Tweets Dataset for Flood, Dust Storm, and Traffic Accident Events",
author = "Hamoui, Btool and
Mars, Mourad and
Almotairi, Khaled",
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.174",
pages = "1391--1396",
abstract = "The rise of social media platforms makes it a valuable information source of recent events and users{'} perspective towards them. Twitter has been one of the most important communication platforms in recent years. Event detection, one of the information extraction aspects, involves identifying specified types of events in the text. Detecting events from tweets can help to predict real-world events precisely. A serious challenge that faces Arabic event detection is the lack of Arabic datasets that can be exploited in detecting events. This paper will describe FloDusTA, which is a dataset of tweets that we have built for the purpose of developing an event detection system. The dataset contains tweets written in both Modern Standard Arabic and Saudi dialect. The process of building the dataset starting from tweets collection to annotation by human annotators will be present. The tweets are labeled with four labels: flood, dust storm, traffic accident, and non-event. The dataset was tested for classification and the result was strongly encouraging.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hamoui-etal-2020-flodusta">
<titleInfo>
<title>FloDusTA: Saudi Tweets Dataset for Flood, Dust Storm, and Traffic Accident Events</title>
</titleInfo>
<name type="personal">
<namePart type="given">Btool</namePart>
<namePart type="family">Hamoui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mourad</namePart>
<namePart type="family">Mars</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khaled</namePart>
<namePart type="family">Almotairi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>The rise of social media platforms makes it a valuable information source of recent events and users’ perspective towards them. Twitter has been one of the most important communication platforms in recent years. Event detection, one of the information extraction aspects, involves identifying specified types of events in the text. Detecting events from tweets can help to predict real-world events precisely. A serious challenge that faces Arabic event detection is the lack of Arabic datasets that can be exploited in detecting events. This paper will describe FloDusTA, which is a dataset of tweets that we have built for the purpose of developing an event detection system. The dataset contains tweets written in both Modern Standard Arabic and Saudi dialect. The process of building the dataset starting from tweets collection to annotation by human annotators will be present. The tweets are labeled with four labels: flood, dust storm, traffic accident, and non-event. The dataset was tested for classification and the result was strongly encouraging.</abstract>
<identifier type="citekey">hamoui-etal-2020-flodusta</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.174</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>1391</start>
<end>1396</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FloDusTA: Saudi Tweets Dataset for Flood, Dust Storm, and Traffic Accident Events
%A Hamoui, Btool
%A Mars, Mourad
%A Almotairi, Khaled
%S Proceedings of the 12th Language Resources and Evaluation Conference
%D 2020
%8 may
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F hamoui-etal-2020-flodusta
%X The rise of social media platforms makes it a valuable information source of recent events and users’ perspective towards them. Twitter has been one of the most important communication platforms in recent years. Event detection, one of the information extraction aspects, involves identifying specified types of events in the text. Detecting events from tweets can help to predict real-world events precisely. A serious challenge that faces Arabic event detection is the lack of Arabic datasets that can be exploited in detecting events. This paper will describe FloDusTA, which is a dataset of tweets that we have built for the purpose of developing an event detection system. The dataset contains tweets written in both Modern Standard Arabic and Saudi dialect. The process of building the dataset starting from tweets collection to annotation by human annotators will be present. The tweets are labeled with four labels: flood, dust storm, traffic accident, and non-event. The dataset was tested for classification and the result was strongly encouraging.
%U https://aclanthology.org/2020.lrec-1.174
%P 1391-1396
Markdown (Informal)
[FloDusTA: Saudi Tweets Dataset for Flood, Dust Storm, and Traffic Accident Events](https://aclanthology.org/2020.lrec-1.174) (Hamoui et al., LREC 2020)
ACL