@inproceedings{dunn-etal-2020-measuring,
title = "Measuring Linguistic Diversity During {COVID}-19",
author = "Dunn, Jonathan and
Coupe, Tom and
Adams, Benjamin",
editor = "Bamman, David and
Hovy, Dirk and
Jurgens, David and
O'Connor, Brendan and
Volkova, Svitlana",
booktitle = "Proceedings of the Fourth Workshop on Natural Language Processing and Computational Social Science",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.nlpcss-1.1",
doi = "10.18653/v1/2020.nlpcss-1.1",
pages = "1--10",
abstract = "Computational measures of linguistic diversity help us understand the linguistic landscape using digital language data. The contribution of this paper is to calibrate measures of linguistic diversity using restrictions on international travel resulting from the COVID-19 pandemic. Previous work has mapped the distribution of languages using geo-referenced social media and web data. The goal, however, has been to describe these corpora themselves rather than to make inferences about underlying populations. This paper shows that a difference-in-differences method based on the Herfindahl-Hirschman Index can identify the bias in digital corpora that is introduced by non-local populations. These methods tell us where significant changes have taken place and whether this leads to increased or decreased diversity. This is an important step in aligning digital corpora like social media with the real-world populations that have produced them.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dunn-etal-2020-measuring">
<titleInfo>
<title>Measuring Linguistic Diversity During COVID-19</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Dunn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Coupe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Adams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Natural Language Processing and Computational Social Science</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Bamman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brendan</namePart>
<namePart type="family">O’Connor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Svitlana</namePart>
<namePart type="family">Volkova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Computational measures of linguistic diversity help us understand the linguistic landscape using digital language data. The contribution of this paper is to calibrate measures of linguistic diversity using restrictions on international travel resulting from the COVID-19 pandemic. Previous work has mapped the distribution of languages using geo-referenced social media and web data. The goal, however, has been to describe these corpora themselves rather than to make inferences about underlying populations. This paper shows that a difference-in-differences method based on the Herfindahl-Hirschman Index can identify the bias in digital corpora that is introduced by non-local populations. These methods tell us where significant changes have taken place and whether this leads to increased or decreased diversity. This is an important step in aligning digital corpora like social media with the real-world populations that have produced them.</abstract>
<identifier type="citekey">dunn-etal-2020-measuring</identifier>
<identifier type="doi">10.18653/v1/2020.nlpcss-1.1</identifier>
<location>
<url>https://aclanthology.org/2020.nlpcss-1.1</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>1</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Measuring Linguistic Diversity During COVID-19
%A Dunn, Jonathan
%A Coupe, Tom
%A Adams, Benjamin
%Y Bamman, David
%Y Hovy, Dirk
%Y Jurgens, David
%Y O’Connor, Brendan
%Y Volkova, Svitlana
%S Proceedings of the Fourth Workshop on Natural Language Processing and Computational Social Science
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F dunn-etal-2020-measuring
%X Computational measures of linguistic diversity help us understand the linguistic landscape using digital language data. The contribution of this paper is to calibrate measures of linguistic diversity using restrictions on international travel resulting from the COVID-19 pandemic. Previous work has mapped the distribution of languages using geo-referenced social media and web data. The goal, however, has been to describe these corpora themselves rather than to make inferences about underlying populations. This paper shows that a difference-in-differences method based on the Herfindahl-Hirschman Index can identify the bias in digital corpora that is introduced by non-local populations. These methods tell us where significant changes have taken place and whether this leads to increased or decreased diversity. This is an important step in aligning digital corpora like social media with the real-world populations that have produced them.
%R 10.18653/v1/2020.nlpcss-1.1
%U https://aclanthology.org/2020.nlpcss-1.1
%U https://doi.org/10.18653/v1/2020.nlpcss-1.1
%P 1-10
Markdown (Informal)
[Measuring Linguistic Diversity During COVID-19](https://aclanthology.org/2020.nlpcss-1.1) (Dunn et al., NLP+CSS 2020)
ACL
- Jonathan Dunn, Tom Coupe, and Benjamin Adams. 2020. Measuring Linguistic Diversity During COVID-19. In Proceedings of the Fourth Workshop on Natural Language Processing and Computational Social Science, pages 1–10, Online. Association for Computational Linguistics.