@inproceedings{miletic-etal-2020-collecting,
title = "Collecting Tweets to Investigate Regional Variation in {C}anadian {E}nglish",
author = "Miletic, Filip and
Przewozny-Desriaux, Anne and
Tanguy, Ludovic",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.767/",
pages = "6255--6264",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "We present a 78.8-million-tweet, 1.3-billion-word corpus aimed at studying regional variation in Canadian English with a specific focus on the dialect regions of Toronto, Montreal, and Vancouver. Our data collection and filtering pipeline reflects complex design criteria, which aim to allow for both data-intensive modeling methods and user-level variationist sociolinguistic analysis. It specifically consists in identifying Twitter users from the three cities, crawling their entire timelines, filtering the collected data in terms of user location and tweet language, and automatically excluding near-duplicate content. The resulting corpus mirrors national and regional specificities of Canadian English, it provides sufficient aggregate and user-level data, and it maintains a reasonably balanced distribution of content across regions and users. The utility of this dataset is illustrated by two example applications: the detection of regional lexical and topical variation, and the identification of contact-induced semantic shifts using vector space models. In accordance with Twitter`s developer policy, the corpus will be publicly released in the form of tweet IDs."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="miletic-etal-2020-collecting">
<titleInfo>
<title>Collecting Tweets to Investigate Regional Variation in Canadian English</title>
</titleInfo>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Miletic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="family">Przewozny-Desriaux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ludovic</namePart>
<namePart type="family">Tanguy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>We present a 78.8-million-tweet, 1.3-billion-word corpus aimed at studying regional variation in Canadian English with a specific focus on the dialect regions of Toronto, Montreal, and Vancouver. Our data collection and filtering pipeline reflects complex design criteria, which aim to allow for both data-intensive modeling methods and user-level variationist sociolinguistic analysis. It specifically consists in identifying Twitter users from the three cities, crawling their entire timelines, filtering the collected data in terms of user location and tweet language, and automatically excluding near-duplicate content. The resulting corpus mirrors national and regional specificities of Canadian English, it provides sufficient aggregate and user-level data, and it maintains a reasonably balanced distribution of content across regions and users. The utility of this dataset is illustrated by two example applications: the detection of regional lexical and topical variation, and the identification of contact-induced semantic shifts using vector space models. In accordance with Twitter‘s developer policy, the corpus will be publicly released in the form of tweet IDs.</abstract>
<identifier type="citekey">miletic-etal-2020-collecting</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.767/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6255</start>
<end>6264</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Collecting Tweets to Investigate Regional Variation in Canadian English
%A Miletic, Filip
%A Przewozny-Desriaux, Anne
%A Tanguy, Ludovic
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G eng
%F miletic-etal-2020-collecting
%X We present a 78.8-million-tweet, 1.3-billion-word corpus aimed at studying regional variation in Canadian English with a specific focus on the dialect regions of Toronto, Montreal, and Vancouver. Our data collection and filtering pipeline reflects complex design criteria, which aim to allow for both data-intensive modeling methods and user-level variationist sociolinguistic analysis. It specifically consists in identifying Twitter users from the three cities, crawling their entire timelines, filtering the collected data in terms of user location and tweet language, and automatically excluding near-duplicate content. The resulting corpus mirrors national and regional specificities of Canadian English, it provides sufficient aggregate and user-level data, and it maintains a reasonably balanced distribution of content across regions and users. The utility of this dataset is illustrated by two example applications: the detection of regional lexical and topical variation, and the identification of contact-induced semantic shifts using vector space models. In accordance with Twitter‘s developer policy, the corpus will be publicly released in the form of tweet IDs.
%U https://aclanthology.org/2020.lrec-1.767/
%P 6255-6264
Markdown (Informal)
[Collecting Tweets to Investigate Regional Variation in Canadian English](https://aclanthology.org/2020.lrec-1.767/) (Miletic et al., LREC 2020)
ACL