ClaimLinker: Linking Text to a Knowledge Graph of Fact-checked Claims

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

  • Evangelos Maliaroudakis
  • Katarina Boland
  • Stefan Dietze
  • Konstantin Todorov
  • Yannis Tzitzikas
  • Pavlos Fafalios

External Research Organisations

  • Foundation for Research & Technology - Hellas (FORTH)
  • University Hospital Düsseldorf
  • GESIS - Leibniz Institute for the Social Sciences
  • Université Montpellier
  • University of Crete
View graph of relations

Details

Original languageEnglish
Title of host publicationThe Web Conference 2021
Subtitle of host publicationCompanion of the World Wide Web Conference
Pages669-672
Number of pages4
ISBN (electronic)978-1-4503-8313-4
Publication statusPublished - 19 Apr 2021
Externally publishedYes
EventWorld Wide Web Conference (WWW 2021) - Ljubljana, Slovenia
Duration: 19 Apr 202123 Apr 2021
Conference number: 30

Abstract

We present ClaimLinker, a Web service and API that links arbitrary text to a knowledge graph of fact-checked claims, offering a novel kind of semantic annotation of unstructured content. Given a text, ClaimLinker matches parts of it to fact-checked claims mined from popular fact-checking sites and integrated into a rich knowledge graph, thus allowing the further exploration of the linked claims and their associations. The application is based on a scalable, fully unsupervised and modular approach that does not require training or tuning and which can serve high quality results at real time (outperforming existing unsupervised methods). This allows its easy deployment for different contexts and application scenarios.

Keywords

    Claim Linking, Claim Retrieval, Fact-checking, Fake News, Knowledge Graphs

ASJC Scopus subject areas

Cite this

ClaimLinker: Linking Text to a Knowledge Graph of Fact-checked Claims. / Maliaroudakis, Evangelos; Boland, Katarina; Dietze, Stefan et al.
The Web Conference 2021: Companion of the World Wide Web Conference. 2021. p. 669-672.

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Maliaroudakis, E, Boland, K, Dietze, S, Todorov, K, Tzitzikas, Y & Fafalios, P 2021, ClaimLinker: Linking Text to a Knowledge Graph of Fact-checked Claims. in The Web Conference 2021: Companion of the World Wide Web Conference. pp. 669-672, World Wide Web Conference (WWW 2021), Ljubljana, Slovenia, 19 Apr 2021. https://doi.org/10.1145/3442442.3458601
Maliaroudakis, E., Boland, K., Dietze, S., Todorov, K., Tzitzikas, Y., & Fafalios, P. (2021). ClaimLinker: Linking Text to a Knowledge Graph of Fact-checked Claims. In The Web Conference 2021: Companion of the World Wide Web Conference (pp. 669-672) https://doi.org/10.1145/3442442.3458601
Maliaroudakis E, Boland K, Dietze S, Todorov K, Tzitzikas Y, Fafalios P. ClaimLinker: Linking Text to a Knowledge Graph of Fact-checked Claims. In The Web Conference 2021: Companion of the World Wide Web Conference. 2021. p. 669-672 doi: 10.1145/3442442.3458601
Maliaroudakis, Evangelos ; Boland, Katarina ; Dietze, Stefan et al. / ClaimLinker : Linking Text to a Knowledge Graph of Fact-checked Claims. The Web Conference 2021: Companion of the World Wide Web Conference. 2021. pp. 669-672
Download
@inproceedings{8ade968ede45473cb67192dc7ca87773,
title = "ClaimLinker: Linking Text to a Knowledge Graph of Fact-checked Claims",
abstract = "We present ClaimLinker, a Web service and API that links arbitrary text to a knowledge graph of fact-checked claims, offering a novel kind of semantic annotation of unstructured content. Given a text, ClaimLinker matches parts of it to fact-checked claims mined from popular fact-checking sites and integrated into a rich knowledge graph, thus allowing the further exploration of the linked claims and their associations. The application is based on a scalable, fully unsupervised and modular approach that does not require training or tuning and which can serve high quality results at real time (outperforming existing unsupervised methods). This allows its easy deployment for different contexts and application scenarios.",
keywords = "Claim Linking, Claim Retrieval, Fact-checking, Fake News, Knowledge Graphs",
author = "Evangelos Maliaroudakis and Katarina Boland and Stefan Dietze and Konstantin Todorov and Yannis Tzitzikas and Pavlos Fafalios",
year = "2021",
month = apr,
day = "19",
doi = "10.1145/3442442.3458601",
language = "English",
pages = "669--672",
booktitle = "The Web Conference 2021",
note = "World Wide Web Conference (WWW 2021), WWW 2021 ; Conference date: 19-04-2021 Through 23-04-2021",

}

Download

TY - GEN

T1 - ClaimLinker

T2 - World Wide Web Conference (WWW 2021)

AU - Maliaroudakis, Evangelos

AU - Boland, Katarina

AU - Dietze, Stefan

AU - Todorov, Konstantin

AU - Tzitzikas, Yannis

AU - Fafalios, Pavlos

N1 - Conference code: 30

PY - 2021/4/19

Y1 - 2021/4/19

N2 - We present ClaimLinker, a Web service and API that links arbitrary text to a knowledge graph of fact-checked claims, offering a novel kind of semantic annotation of unstructured content. Given a text, ClaimLinker matches parts of it to fact-checked claims mined from popular fact-checking sites and integrated into a rich knowledge graph, thus allowing the further exploration of the linked claims and their associations. The application is based on a scalable, fully unsupervised and modular approach that does not require training or tuning and which can serve high quality results at real time (outperforming existing unsupervised methods). This allows its easy deployment for different contexts and application scenarios.

AB - We present ClaimLinker, a Web service and API that links arbitrary text to a knowledge graph of fact-checked claims, offering a novel kind of semantic annotation of unstructured content. Given a text, ClaimLinker matches parts of it to fact-checked claims mined from popular fact-checking sites and integrated into a rich knowledge graph, thus allowing the further exploration of the linked claims and their associations. The application is based on a scalable, fully unsupervised and modular approach that does not require training or tuning and which can serve high quality results at real time (outperforming existing unsupervised methods). This allows its easy deployment for different contexts and application scenarios.

KW - Claim Linking

KW - Claim Retrieval

KW - Fact-checking

KW - Fake News

KW - Knowledge Graphs

UR - http://www.scopus.com/inward/record.url?scp=85107676790&partnerID=8YFLogxK

U2 - 10.1145/3442442.3458601

DO - 10.1145/3442442.3458601

M3 - Conference contribution

AN - SCOPUS:85107676790

SP - 669

EP - 672

BT - The Web Conference 2021

Y2 - 19 April 2021 through 23 April 2021

ER -