@inproceedings{aker-etal-2012-assessing,
title = "Assessing Crowdsourcing Quality through Objective Tasks",
author = "Aker, Ahmet and
El-Haj, Mahmoud and
Albakour, M-Dyaa and
Kruschwitz, Udo",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/583_Paper.pdf",
pages = "1456--1461",
abstract = "The emergence of crowdsourcing as a commonly used approach to collect vast quantities of human assessments on a variety of tasks represents nothing less than a paradigm shift. This is particularly true in academic research where it has suddenly become possible to collect (high-quality) annotations rapidly without the need of an expert. In this paper we investigate factors which can influence the quality of the results obtained through Amazon's Mechanical Turk crowdsourcing platform. We investigated the impact of different presentation methods (free text versus radio buttons), workers' base (USA versus India as the main bases of MTurk workers) and payment scale (about {\$}4, {\$}8 and {\$}10 per hour) on the quality of the results. For each run we assessed the results provided by 25 workers on a set of 10 tasks. We run two different experiments using objective tasks: maths and general text questions. In both tasks the answers are unique, which eliminates the uncertainty usually present in subjective tasks, where it is not clear whether the unexpected answer is caused by a lack of worker's motivation, the worker's interpretation of the task or genuine ambiguity. In this work we present our results comparing the influence of the different factors used. One of the interesting findings is that our results do not confirm previous studies which concluded that an increase in payment attracts more noise. We also find that the country of origin only has an impact in some of the categories and only in general text questions but there is no significant difference at the top pay.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aker-etal-2012-assessing">
<titleInfo>
<title>Assessing Crowdsourcing Quality through Objective Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmet</namePart>
<namePart type="family">Aker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">M-Dyaa</namePart>
<namePart type="family">Albakour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Udo</namePart>
<namePart type="family">Kruschwitz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The emergence of crowdsourcing as a commonly used approach to collect vast quantities of human assessments on a variety of tasks represents nothing less than a paradigm shift. This is particularly true in academic research where it has suddenly become possible to collect (high-quality) annotations rapidly without the need of an expert. In this paper we investigate factors which can influence the quality of the results obtained through Amazon’s Mechanical Turk crowdsourcing platform. We investigated the impact of different presentation methods (free text versus radio buttons), workers’ base (USA versus India as the main bases of MTurk workers) and payment scale (about $4, $8 and $10 per hour) on the quality of the results. For each run we assessed the results provided by 25 workers on a set of 10 tasks. We run two different experiments using objective tasks: maths and general text questions. In both tasks the answers are unique, which eliminates the uncertainty usually present in subjective tasks, where it is not clear whether the unexpected answer is caused by a lack of worker’s motivation, the worker’s interpretation of the task or genuine ambiguity. In this work we present our results comparing the influence of the different factors used. One of the interesting findings is that our results do not confirm previous studies which concluded that an increase in payment attracts more noise. We also find that the country of origin only has an impact in some of the categories and only in general text questions but there is no significant difference at the top pay.</abstract>
<identifier type="citekey">aker-etal-2012-assessing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/583_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>1456</start>
<end>1461</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Assessing Crowdsourcing Quality through Objective Tasks
%A Aker, Ahmet
%A El-Haj, Mahmoud
%A Albakour, M-Dyaa
%A Kruschwitz, Udo
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F aker-etal-2012-assessing
%X The emergence of crowdsourcing as a commonly used approach to collect vast quantities of human assessments on a variety of tasks represents nothing less than a paradigm shift. This is particularly true in academic research where it has suddenly become possible to collect (high-quality) annotations rapidly without the need of an expert. In this paper we investigate factors which can influence the quality of the results obtained through Amazon’s Mechanical Turk crowdsourcing platform. We investigated the impact of different presentation methods (free text versus radio buttons), workers’ base (USA versus India as the main bases of MTurk workers) and payment scale (about $4, $8 and $10 per hour) on the quality of the results. For each run we assessed the results provided by 25 workers on a set of 10 tasks. We run two different experiments using objective tasks: maths and general text questions. In both tasks the answers are unique, which eliminates the uncertainty usually present in subjective tasks, where it is not clear whether the unexpected answer is caused by a lack of worker’s motivation, the worker’s interpretation of the task or genuine ambiguity. In this work we present our results comparing the influence of the different factors used. One of the interesting findings is that our results do not confirm previous studies which concluded that an increase in payment attracts more noise. We also find that the country of origin only has an impact in some of the categories and only in general text questions but there is no significant difference at the top pay.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/583_Paper.pdf
%P 1456-1461
Markdown (Informal)
[Assessing Crowdsourcing Quality through Objective Tasks](http://www.lrec-conf.org/proceedings/lrec2012/pdf/583_Paper.pdf) (Aker et al., LREC 2012)
ACL
- Ahmet Aker, Mahmoud El-Haj, M-Dyaa Albakour, and Udo Kruschwitz. 2012. Assessing Crowdsourcing Quality through Objective Tasks. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 1456–1461, Istanbul, Turkey. European Language Resources Association (ELRA).