Abstract | ||
---|---|---|
Various research areas at the intersection of computer and social sciences require a ground truth of contextualized claims labelled with their truth values in order to facilitate supervision, validation or reproducibility of approaches dealing, for example, with fact-checking or analysis of societal debates. So far, no reasonably large, up-to-date and queryable corpus of structured information about claims and related metadata is publicly available. In an attempt to fill this gap, we introduce ClaimsKG, a knowledge graph of fact-checked claims, which facilitates structured queries about their truth values, authors, dates, journalistic reviews and other kinds of metadata. ClaimsKG is generated through a semi-automated pipeline, which harvests data from popular fact-checking websites on a regular basis, annotates claims with related entities from DBpedia, and lifts the data to RDF using an RDF/S model that makes use of established vocabularies. In order to harmonise data originating from diverse fact-checking sites, we introduce normalised ratings as well as a simple claims coreference resolution strategy. The current knowledge graph, extensible to new information, consists of 28,383 claims published since 1996, amounting to 6,606,032 triples. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1007/978-3-030-30796-7_20 | Lecture Notes in Computer Science |
Keywords | DocType | Volume |
Claims,Fact-checking,Societal debates,Knowledge graphs | Conference | 11779 |
ISSN | Citations | PageRank |
0302-9743 | 2 | 0.39 |
References | Authors | |
0 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Andon Tchechmedjiev | 1 | 21 | 8.43 |
Pavlos Fafalios | 2 | 154 | 19.76 |
Katarina Boland | 3 | 4 | 2.26 |
Malo Gasquet | 4 | 2 | 0.39 |
Matthäus Zloch | 5 | 2 | 1.41 |
Benjamin Zapilko | 6 | 59 | 14.01 |
Stefan Dietze | 7 | 597 | 68.07 |
Konstantin Todorov | 8 | 103 | 14.57 |