@inproceedings{capuozzo-etal-2020-decop,
title = "{D}ec{O}p: A Multilingual and Multi-domain Corpus For Detecting Deception In Typed Text",
author = "Capuozzo, Pasquale and
Lauriola, Ivano and
Strapparava, Carlo and
Aiolli, Fabio and
Sartori, Giuseppe",
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.178",
pages = "1423--1430",
abstract = "In recent years, the increasing interest in the development of automatic approaches for unmasking deception in online sources led to promising results. Nonetheless, among the others, two major issues remain still unsolved: the stability of classifiers performances across different domains and languages. Tackling these issues is challenging since labelled corpora involving multiple domains and compiled in more than one language are few in the scientific literature. For filling this gap, in this paper we introduce DecOp (Deceptive Opinions), a new language resource developed for automatic deception detection in cross-domain and cross-language scenarios. DecOp is composed of 5000 examples of both truthful and deceitful first-person opinions balanced both across five different domains and two languages and, to the best of our knowledge, is the largest corpus allowing cross-domain and cross-language comparisons in deceit detection tasks. In this paper, we describe the collection procedure of the DecOp corpus and his main characteristics. Moreover, the human performance on the DecOp test-set and preliminary experiments by means of machine learning models based on Transformer architecture are shown.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="capuozzo-etal-2020-decop">
<titleInfo>
<title>DecOp: A Multilingual and Multi-domain Corpus For Detecting Deception In Typed Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pasquale</namePart>
<namePart type="family">Capuozzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivano</namePart>
<namePart type="family">Lauriola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlo</namePart>
<namePart type="family">Strapparava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Aiolli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Sartori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<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>In recent years, the increasing interest in the development of automatic approaches for unmasking deception in online sources led to promising results. Nonetheless, among the others, two major issues remain still unsolved: the stability of classifiers performances across different domains and languages. Tackling these issues is challenging since labelled corpora involving multiple domains and compiled in more than one language are few in the scientific literature. For filling this gap, in this paper we introduce DecOp (Deceptive Opinions), a new language resource developed for automatic deception detection in cross-domain and cross-language scenarios. DecOp is composed of 5000 examples of both truthful and deceitful first-person opinions balanced both across five different domains and two languages and, to the best of our knowledge, is the largest corpus allowing cross-domain and cross-language comparisons in deceit detection tasks. In this paper, we describe the collection procedure of the DecOp corpus and his main characteristics. Moreover, the human performance on the DecOp test-set and preliminary experiments by means of machine learning models based on Transformer architecture are shown.</abstract>
<identifier type="citekey">capuozzo-etal-2020-decop</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.178</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>1423</start>
<end>1430</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DecOp: A Multilingual and Multi-domain Corpus For Detecting Deception In Typed Text
%A Capuozzo, Pasquale
%A Lauriola, Ivano
%A Strapparava, Carlo
%A Aiolli, Fabio
%A Sartori, Giuseppe
%S Proceedings of the 12th Language Resources and Evaluation Conference
%D 2020
%8 may
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F capuozzo-etal-2020-decop
%X In recent years, the increasing interest in the development of automatic approaches for unmasking deception in online sources led to promising results. Nonetheless, among the others, two major issues remain still unsolved: the stability of classifiers performances across different domains and languages. Tackling these issues is challenging since labelled corpora involving multiple domains and compiled in more than one language are few in the scientific literature. For filling this gap, in this paper we introduce DecOp (Deceptive Opinions), a new language resource developed for automatic deception detection in cross-domain and cross-language scenarios. DecOp is composed of 5000 examples of both truthful and deceitful first-person opinions balanced both across five different domains and two languages and, to the best of our knowledge, is the largest corpus allowing cross-domain and cross-language comparisons in deceit detection tasks. In this paper, we describe the collection procedure of the DecOp corpus and his main characteristics. Moreover, the human performance on the DecOp test-set and preliminary experiments by means of machine learning models based on Transformer architecture are shown.
%U https://aclanthology.org/2020.lrec-1.178
%P 1423-1430
Markdown (Informal)
[DecOp: A Multilingual and Multi-domain Corpus For Detecting Deception In Typed Text](https://aclanthology.org/2020.lrec-1.178) (Capuozzo et al., LREC 2020)
ACL