A context-aware approach for detecting worth-checking claims in political debates

Pepa Gencheva, Preslav Nakov, Lluis Marques, Alberto Barron, Ivan Koychev

Research output: Chapter in Book/Report/Conference proceedingConference contribution

16 Citations (Scopus)

Abstract

In the context of investigative journalism, we address the problem of automatically identifying which claims in a given document are most worthy and should be prioritized for fact-checking. Despite its importance, this is a relatively understudied problem. Thus, we create a new corpus of political debates, containing statements that have been fact-checked by nine reputable sources, and we train machine learning models to predict which claims should be prioritized for fact-checking, i.e., we model the problem as a ranking task. Unlike previous work, which has looked primarily at sentences in isolation, in this paper we focus on a rich input representation modeling the context: relationship between the target statement and the larger context of the debate, interaction between the opponents, and reaction by the moderator and by the public. Our experiments show state-of-the-art results, outperforming a strong rivaling system by a margin, while also confirming the importance of the contextual information.

Original languageEnglish
Title of host publicationInternational Conference on Recent Advances in Natural Language Processing
Subtitle of host publicationMeet Deep Learning, RANLP 2017 - Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages267-276
Number of pages10
Volume2017-September
ISBN (Electronic)9789544520489
DOIs
Publication statusPublished - 1 Jan 2017
Event11th International Conference on Recent Advances in Natural Language Processing, RANLP 2017 - Varna, Bulgaria
Duration: 2 Sep 20178 Sep 2017

Other

Other11th International Conference on Recent Advances in Natural Language Processing, RANLP 2017
CountryBulgaria
CityVarna
Period2/9/178/9/17

Fingerprint

Moderators
Learning systems
Experiments

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Software
  • Electrical and Electronic Engineering

Cite this

Gencheva, P., Nakov, P., Marques, L., Barron, A., & Koychev, I. (2017). A context-aware approach for detecting worth-checking claims in political debates. In International Conference on Recent Advances in Natural Language Processing: Meet Deep Learning, RANLP 2017 - Proceedings (Vol. 2017-September, pp. 267-276). Association for Computational Linguistics (ACL). https://doi.org/10.26615/978-954-452-049-6-037

A context-aware approach for detecting worth-checking claims in political debates. / Gencheva, Pepa; Nakov, Preslav; Marques, Lluis; Barron, Alberto; Koychev, Ivan.

International Conference on Recent Advances in Natural Language Processing: Meet Deep Learning, RANLP 2017 - Proceedings. Vol. 2017-September Association for Computational Linguistics (ACL), 2017. p. 267-276.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Gencheva, P, Nakov, P, Marques, L, Barron, A & Koychev, I 2017, A context-aware approach for detecting worth-checking claims in political debates. in International Conference on Recent Advances in Natural Language Processing: Meet Deep Learning, RANLP 2017 - Proceedings. vol. 2017-September, Association for Computational Linguistics (ACL), pp. 267-276, 11th International Conference on Recent Advances in Natural Language Processing, RANLP 2017, Varna, Bulgaria, 2/9/17. https://doi.org/10.26615/978-954-452-049-6-037
Gencheva P, Nakov P, Marques L, Barron A, Koychev I. A context-aware approach for detecting worth-checking claims in political debates. In International Conference on Recent Advances in Natural Language Processing: Meet Deep Learning, RANLP 2017 - Proceedings. Vol. 2017-September. Association for Computational Linguistics (ACL). 2017. p. 267-276 https://doi.org/10.26615/978-954-452-049-6-037
Gencheva, Pepa ; Nakov, Preslav ; Marques, Lluis ; Barron, Alberto ; Koychev, Ivan. / A context-aware approach for detecting worth-checking claims in political debates. International Conference on Recent Advances in Natural Language Processing: Meet Deep Learning, RANLP 2017 - Proceedings. Vol. 2017-September Association for Computational Linguistics (ACL), 2017. pp. 267-276
@inproceedings{1c4abbf334004ca9aa1c514d07a28533,
title = "A context-aware approach for detecting worth-checking claims in political debates",
abstract = "In the context of investigative journalism, we address the problem of automatically identifying which claims in a given document are most worthy and should be prioritized for fact-checking. Despite its importance, this is a relatively understudied problem. Thus, we create a new corpus of political debates, containing statements that have been fact-checked by nine reputable sources, and we train machine learning models to predict which claims should be prioritized for fact-checking, i.e., we model the problem as a ranking task. Unlike previous work, which has looked primarily at sentences in isolation, in this paper we focus on a rich input representation modeling the context: relationship between the target statement and the larger context of the debate, interaction between the opponents, and reaction by the moderator and by the public. Our experiments show state-of-the-art results, outperforming a strong rivaling system by a margin, while also confirming the importance of the contextual information.",
author = "Pepa Gencheva and Preslav Nakov and Lluis Marques and Alberto Barron and Ivan Koychev",
year = "2017",
month = "1",
day = "1",
doi = "10.26615/978-954-452-049-6-037",
language = "English",
volume = "2017-September",
pages = "267--276",
booktitle = "International Conference on Recent Advances in Natural Language Processing",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - A context-aware approach for detecting worth-checking claims in political debates

AU - Gencheva, Pepa

AU - Nakov, Preslav

AU - Marques, Lluis

AU - Barron, Alberto

AU - Koychev, Ivan

PY - 2017/1/1

Y1 - 2017/1/1

N2 - In the context of investigative journalism, we address the problem of automatically identifying which claims in a given document are most worthy and should be prioritized for fact-checking. Despite its importance, this is a relatively understudied problem. Thus, we create a new corpus of political debates, containing statements that have been fact-checked by nine reputable sources, and we train machine learning models to predict which claims should be prioritized for fact-checking, i.e., we model the problem as a ranking task. Unlike previous work, which has looked primarily at sentences in isolation, in this paper we focus on a rich input representation modeling the context: relationship between the target statement and the larger context of the debate, interaction between the opponents, and reaction by the moderator and by the public. Our experiments show state-of-the-art results, outperforming a strong rivaling system by a margin, while also confirming the importance of the contextual information.

AB - In the context of investigative journalism, we address the problem of automatically identifying which claims in a given document are most worthy and should be prioritized for fact-checking. Despite its importance, this is a relatively understudied problem. Thus, we create a new corpus of political debates, containing statements that have been fact-checked by nine reputable sources, and we train machine learning models to predict which claims should be prioritized for fact-checking, i.e., we model the problem as a ranking task. Unlike previous work, which has looked primarily at sentences in isolation, in this paper we focus on a rich input representation modeling the context: relationship between the target statement and the larger context of the debate, interaction between the opponents, and reaction by the moderator and by the public. Our experiments show state-of-the-art results, outperforming a strong rivaling system by a margin, while also confirming the importance of the contextual information.

UR - http://www.scopus.com/inward/record.url?scp=85045755224&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045755224&partnerID=8YFLogxK

U2 - 10.26615/978-954-452-049-6-037

DO - 10.26615/978-954-452-049-6-037

M3 - Conference contribution

VL - 2017-September

SP - 267

EP - 276

BT - International Conference on Recent Advances in Natural Language Processing

PB - Association for Computational Linguistics (ACL)

ER -