Beyond facts – a survey and conceptualisation of claims in online discourse analysis

Boland, Katarina; Fafalios, Pavlos; Tchechmedjiev, Andon; Dietze, Stefan; Todorov, Konstantin

doi:10.3233/sw-212838

Cited by 3 publications

(2 citation statements)

References 194 publications

(265 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The input claims themselves are individual sentences from the speeches, yet they sometimes refer to entities mentioned in the context rather than the claims themselves, and can depend on one another, as can be seen in Table 6. With this, the data can be seen as diverging from the task definition defining a check-worthy claim as input, as the individual queries in this dataset are not necessarily check-worthy by themselves and do not constitute individual claims, depending on the precise definition of what a claim is (see [4] for an overview of diverging definitions), which is left implicit in this task definition. In both the 2021 and 2022 datasets, the input query IDs contain the date of the debate which can be used as a feature to compare with the verified claim dates (cf.…”

Section: Political Debates Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

Robust and Efficient Claim Retrieval for Online Fact-Checking Applications

Boland,

Hövelmeyer,

Fafalios

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Understanding the veracity of statements is important when consuming information on the Web. Whereas fact-checking sites have provided a large corpus of already verified claims, matching a given utterance to already fact-checked claims remains a challenging task. Verified claim retrieval has been approached through a variety of different methods, among them approaches relying on supervised neural models. Whereas such models tend to perform strongly, they require significant training effort and their robustness towards unseen data distributions may vary heavily. Also, prior works demonstrate the capability of unsupervised models to provide state-of-the-art performance.In this paper, we assess established claim retrieval benchmark datasets and experimentally evaluate and compare different state-of-the-art supervised and unsupervised methods with regard to performance, but also computational effort and run time. We show that unsupervised approaches outperform supervised ones with respect to robustness. While the best state-of-the-art method relies on supervised deep neural networks, its high computational costs make it difficult to use in online fact-checking applications. The best unsupervised method reaches a similar performance and meets efficiency requirements of online application scenarios due to low hardware requirements. Our experiments verify that, due to the nature of the task and data, the choice of pre-trained language models is more important than fine-tuning and that training supervised models on the target data may not be cost-efficient in online claim retrieval applications.

show abstract

Section: Political Debates Datasetsmentioning

confidence: 99%

“…However, given that a particular claim proposition may occur in the form of diverse utterances [4], matching a given statement or utterance to fact-checked claims available from fact-checking portals remains a challenging problem. This problem is known as verified claim retrieval and has been recognised by the Check That!…”

Section: Introductionmentioning

confidence: 99%