@inproceedings{salvetti-etal-2016-tangled,
title = "A Tangled Web: The Faint Signals of Deception in Text - Boulder Lies and Truth Corpus ({BLT}-{C})",
author = "Salvetti, Franco and
Lowe, John B. and
Martin, James H.",
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/L16-1558",
pages = "3510--3517",
abstract = "We present an approach to creating corpora for use in detecting deception in text, including a discussion of the challenges peculiar to this task. Our approach is based on soliciting several types of reviews from writers and was implemented using Amazon Mechanical Turk. We describe the multi-dimensional corpus of reviews built using this approach, available free of charge from LDC as the Boulder Lies and Truth Corpus (BLT-C). Challenges for both corpus creation and the deception detection include the fact that human performance on the task is typically at chance, that the signal is faint, that paid writers such as turkers are sometimes deceptive, and that deception is a complex human behavior; manifestations of deception depend on details of domain, intrinsic properties of the deceiver (such as education, linguistic competence, and the nature of the intention), and specifics of the deceptive act (e.g., lying vs. fabricating.) To overcome the inherent lack of ground truth, we have developed a set of semi-automatic techniques to ensure corpus validity. We present some preliminary results on the task of deception detection which suggest that the BLT-C is an improvement in the quality of resources available for this task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="salvetti-etal-2016-tangled">
<titleInfo>
<title>A Tangled Web: The Faint Signals of Deception in Text - Boulder Lies and Truth Corpus (BLT-C)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Franco</namePart>
<namePart type="family">Salvetti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">B</namePart>
<namePart type="family">Lowe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="given">H</namePart>
<namePart type="family">Martin</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>We present an approach to creating corpora for use in detecting deception in text, including a discussion of the challenges peculiar to this task. Our approach is based on soliciting several types of reviews from writers and was implemented using Amazon Mechanical Turk. We describe the multi-dimensional corpus of reviews built using this approach, available free of charge from LDC as the Boulder Lies and Truth Corpus (BLT-C). Challenges for both corpus creation and the deception detection include the fact that human performance on the task is typically at chance, that the signal is faint, that paid writers such as turkers are sometimes deceptive, and that deception is a complex human behavior; manifestations of deception depend on details of domain, intrinsic properties of the deceiver (such as education, linguistic competence, and the nature of the intention), and specifics of the deceptive act (e.g., lying vs. fabricating.) To overcome the inherent lack of ground truth, we have developed a set of semi-automatic techniques to ensure corpus validity. We present some preliminary results on the task of deception detection which suggest that the BLT-C is an improvement in the quality of resources available for this task.</abstract>
<identifier type="citekey">salvetti-etal-2016-tangled</identifier>
<location>
<url>https://aclanthology.org/L16-1558</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3510</start>
<end>3517</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Tangled Web: The Faint Signals of Deception in Text - Boulder Lies and Truth Corpus (BLT-C)
%A Salvetti, Franco
%A Lowe, John B.
%A Martin, James H.
%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 salvetti-etal-2016-tangled
%X We present an approach to creating corpora for use in detecting deception in text, including a discussion of the challenges peculiar to this task. Our approach is based on soliciting several types of reviews from writers and was implemented using Amazon Mechanical Turk. We describe the multi-dimensional corpus of reviews built using this approach, available free of charge from LDC as the Boulder Lies and Truth Corpus (BLT-C). Challenges for both corpus creation and the deception detection include the fact that human performance on the task is typically at chance, that the signal is faint, that paid writers such as turkers are sometimes deceptive, and that deception is a complex human behavior; manifestations of deception depend on details of domain, intrinsic properties of the deceiver (such as education, linguistic competence, and the nature of the intention), and specifics of the deceptive act (e.g., lying vs. fabricating.) To overcome the inherent lack of ground truth, we have developed a set of semi-automatic techniques to ensure corpus validity. We present some preliminary results on the task of deception detection which suggest that the BLT-C is an improvement in the quality of resources available for this task.
%U https://aclanthology.org/L16-1558
%P 3510-3517
Markdown (Informal)
[A Tangled Web: The Faint Signals of Deception in Text - Boulder Lies and Truth Corpus (BLT-C)](https://aclanthology.org/L16-1558) (Salvetti et al., LREC 2016)
ACL