AraStance: A Multi-Country and Multi-Domain Dataset of Arabic Stance Detection for Fact Checking

Alhindi, Tariq; Alabdulkarim, Amal; Alshehri, Ali; Abdul-Mageed, Muhammad; Nakov, Preslav

doi:10.18653/v1/2021.nlp4if-1.9

Cited by 11 publications

(9 citation statements)

References 21 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For true and false rumors, we selected a single tweet example and all provided evidence tweets, which are then labeled as having agree and disagree stances respectively. 3 If the fact-checkers provided the authority account but stated no evidence was found to support or deny the rumor, we selected one or two tweets from the authority timeline posted soon before the rumor time, and assigned the unrelated label to the pairs. Exploiting Authority Accounts.…”

Section: Constructing Austr Datasetmentioning

confidence: 99%

“…Several studies addressed Arabic stance detection in Twitter; however, the target was a specific topic not rumors [15,22,6]. A few datasets for stance detection for Arabic claim verification were released recently, where the evidence is either news articles [10,3] or manually-crafted sentences [23]. However, there is no dataset where the rumors are tweets and the evidence is retrieved from authority timelines, neither in Arabic nor in other languages.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detecting Stance of Authorities towards Rumors in Arabic Tweets: A Preliminary Study

Haouari¹,

Elsayed²

2023

Preprint

View full text Add to dashboard Cite

A myriad of studies addressed the problem of rumor verification in Twitter by either utilizing evidence from the propagation networks or external evidence from the Web. However, none of these studies exploited evidence from trusted authorities. In this paper, we define the task of detecting the stance of authorities towards rumors in tweets, i.e., whether a tweet from an authority agrees, disagrees, or is unrelated to the rumor. We believe the task is useful to augment the sources of evidence utilized by existing rumor verification systems. We construct and release the first Authority STance towards Rumors (AuSTR) dataset, where evidence is retrieved from authority timelines in Arabic Twitter. Due to the relatively limited size of our dataset, we study the usefulness of existing datasets for stance detection in our task. We show that existing datasets are somewhat useful for the task; however, they are clearly insufficient, which motivates the need to augment them with annotated data constituting stance of authorities from Twitter.

show abstract

Section: Constructing Austr Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Detecting Stance of Authorities towards Rumors in Arabic Tweets: A Preliminary Study

Haouari¹,

Elsayed²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Automatic claim verification shows remarkable progress with the introduction of rich claim verification datasets (Vlachos and Riedel, 2014;Thorne et al, 2018;Hanselowski et al, 2019;Aly et al, 2021;Khan et al, 2022). Existing claim verification datasets introduce many variants, including shift in domains and languages of claims; claims from political sources (Wang, 2017), scientific claims (Wadden et al, 2020), climate changerelated claims (Leippold and Diggelmann, 2020), Arabic claims (Baly et al, 2018;Alhindi et al, 2021), and Danish claims (Nørregaard and Derczynski, 2021). Our assumption is different from claim verification in that one claim is not necessarily more true than the other, resulting the need for comparison between claims rather than verification.…”

Section: Related Workmentioning

confidence: 99%

Beyond Fact Verification: Comparing and Contrasting Claims on Contentious Topics

Ko¹,

Ingyu²,

Lee³

et al. 2022

Preprint

View full text Add to dashboard Cite

As the importance of identifying misinformation is increasing, many researchers focus on verifying textual claims on the web. One of the most popular tasks to achieve this is fact verification, which retrieves an evidence sentence from a large knowledge source such as Wikipedia to either verify or refute each factual claim. However, while such problem formulation is helpful for detecting false claims and fake news, it is not applicable to catching subtle differences in factually consistent claims which still might implicitly bias the readers, especially in contentious topics such as political, gender, or racial issues. In this study, we propose ClaimDiff, a novel dataset to compare the nuance between claim pairs in both a discriminative and a generative manner, with the underlying assumption that one is not necessarily more true than the other. This differs from existing fact verification datasets that verify the target sentence with respect to an absolute truth. We hope this task assists people in making more informed decisions among various sources of media.

show abstract

“…Yet, for stance detection, multilingual resources remain scarce (Joshi et al 2020). While English datasets exist for various domains and of different sizes, non-English and multilingual datasets are often small -under a thousand examples (Lai et al 2018(Lai et al , 2020Lozhnikov, Derczynski, and Mazzara 2020;Alhindi et al 2021)-, and focus on narrow, potentially country-or culture-specific topics, such as a referendum (Taulé et al 2017;Lai et al 2018), a person (Hercig et al 2017;Darwish et al 2020;Lai et al 2020), or a notable event (Swami et al 2018), with few exceptions (Vamvas and Sennrich 2020).…”

Section: Introductionmentioning

confidence: 99%

Few-Shot Cross-Lingual Stance Detection with Sentiment-Based Pre-training

Hardalov

Arora

Nakov

et al. 2022

AAAI

Self Cite

View full text Add to dashboard Cite

The goal of stance detection is to determine the viewpoint expressed in a piece of text towards a target. These viewpoints or contexts are often expressed in many different languages depending on the user and the platform, which can be a local news outlet, a social media platform, a news forum, etc. Most research on stance detection, however, has been limited to working with a single language and on a few limited targets, with little work on cross-lingual stance detection. Moreover, non-English sources of labelled data are often scarce and present additional challenges. Recently, large multilingual language models have substantially improved the performance on many non-English tasks, especially such with a limited number of examples. This highlights the importance of model pre-training and its ability to learn from few examples. In this paper, we present the most comprehensive study of cross-lingual stance detection to date: we experiment with 15 diverse datasets in 12 languages from 6 language families, and with 6 low-resource evaluation settings each. For our experiments, we build on pattern-exploiting training (PET), proposing the addition of a novel label encoder to simplify the verbalisation procedure. We further propose sentiment-based generation of stance data for pre-training, which shows sizeable improvement of more than 6% F1 absolute in few-shot learning settings compared to several strong baselines.

show abstract

AraStance: A Multi-Country and Multi-Domain Dataset of Arabic Stance Detection for Fact Checking

Cited by 11 publications

References 21 publications

Detecting Stance of Authorities towards Rumors in Arabic Tweets: A Preliminary Study

Detecting Stance of Authorities towards Rumors in Arabic Tweets: A Preliminary Study

Beyond Fact Verification: Comparing and Contrasting Claims on Contentious Topics

Few-Shot Cross-Lingual Stance Detection with Sentiment-Based Pre-training

Contact Info

Product

Resources

About