@inproceedings{yates-etal-2016-effects,
title = "Effects of Sampling on {T}witter Trend Detection",
author = "Yates, Andrew and
Kolcz, Alek and
Goharian, Nazli and
Frieder, Ophir",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}`16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1479/",
pages = "2998--3005",
abstract = "Much research has focused on detecting trends on Twitter, including health-related trends such as mentions of Influenza-like illnesses or their symptoms. The majority of this research has been conducted using Twitter`s public feed, which includes only about 1{\%} of all public tweets. It is unclear if, when, and how using Twitter`s 1{\%} feed has affected the evaluation of trend detection methods. In this work we use a larger feed to investigate the effects of sampling on Twitter trend detection. We focus on using health-related trends to estimate the prevalence of Influenza-like illnesses based on tweets. We use ground truth obtained from the CDC and Google Flu Trends to explore how the prevalence estimates degrade when moving from a 100{\%} to a 1{\%} sample. We find that using the 1{\%} sample is unlikely to substantially harm ILI estimates made at the national level, but can cause poor performance when estimates are made at the city level."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yates-etal-2016-effects">
<titleInfo>
<title>Effects of Sampling on Twitter Trend Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Yates</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alek</namePart>
<namePart type="family">Kolcz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nazli</namePart>
<namePart type="family">Goharian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ophir</namePart>
<namePart type="family">Frieder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC‘16)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Much research has focused on detecting trends on Twitter, including health-related trends such as mentions of Influenza-like illnesses or their symptoms. The majority of this research has been conducted using Twitter‘s public feed, which includes only about 1% of all public tweets. It is unclear if, when, and how using Twitter‘s 1% feed has affected the evaluation of trend detection methods. In this work we use a larger feed to investigate the effects of sampling on Twitter trend detection. We focus on using health-related trends to estimate the prevalence of Influenza-like illnesses based on tweets. We use ground truth obtained from the CDC and Google Flu Trends to explore how the prevalence estimates degrade when moving from a 100% to a 1% sample. We find that using the 1% sample is unlikely to substantially harm ILI estimates made at the national level, but can cause poor performance when estimates are made at the city level.</abstract>
<identifier type="citekey">yates-etal-2016-effects</identifier>
<location>
<url>https://aclanthology.org/L16-1479/</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>2998</start>
<end>3005</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Effects of Sampling on Twitter Trend Detection
%A Yates, Andrew
%A Kolcz, Alek
%A Goharian, Nazli
%A Frieder, Ophir
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC‘16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F yates-etal-2016-effects
%X Much research has focused on detecting trends on Twitter, including health-related trends such as mentions of Influenza-like illnesses or their symptoms. The majority of this research has been conducted using Twitter‘s public feed, which includes only about 1% of all public tweets. It is unclear if, when, and how using Twitter‘s 1% feed has affected the evaluation of trend detection methods. In this work we use a larger feed to investigate the effects of sampling on Twitter trend detection. We focus on using health-related trends to estimate the prevalence of Influenza-like illnesses based on tweets. We use ground truth obtained from the CDC and Google Flu Trends to explore how the prevalence estimates degrade when moving from a 100% to a 1% sample. We find that using the 1% sample is unlikely to substantially harm ILI estimates made at the national level, but can cause poor performance when estimates are made at the city level.
%U https://aclanthology.org/L16-1479/
%P 2998-3005
Markdown (Informal)
[Effects of Sampling on Twitter Trend Detection](https://aclanthology.org/L16-1479/) (Yates et al., LREC 2016)
ACL
- Andrew Yates, Alek Kolcz, Nazli Goharian, and Ophir Frieder. 2016. Effects of Sampling on Twitter Trend Detection. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 2998–3005, Portorož, Slovenia. European Language Resources Association (ELRA).