FactRank: Developing automated claim detection for Dutch-language fact-checkers

Berendt, Bettina; Burger, Peter; Hautekiet, Rafael; Jagers, Jan; Pleijter, A.R.J.; Aelst, Peter Van

doi:10.1016/j.osnem.2020.100113

Cited by 13 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, publicly available datasets have a variety of sizes. For instance, ClaimBuster (Arslan et al, 2020) and CT19-T1 are the largest datasets, while CW- USPD-2016(Gencheva et al, 2017, CT-CWC-18 (Atanasova et al, 2018), CT20-AR and FactRank (Berendt et al, 2020) are a degree of magnitude smaller, followed by other smaller datasets.…”

Section: Datasetsmentioning

confidence: 99%

“…Likewise fine-tuned multilingual BERT (mBERT) with different classification models. Another recent effort, called FactRank (Berendt et al, 2020), focused on claim check-worthiness detection for the Dutch language, in this case using a convolutional neural network (CNN) along with Platt scaling for an SVM model and a softmax to obtain the degree of check-worthiness.…”

Section: Check-worthy Claim Detectionmentioning

confidence: 99%

“…In contrast (Konstantinovskiy et al, 2021), mentioned this definition is not enough to decide whether this claim is worthy for check or not. Similarly, Berendt et al (2020) declared that not every factual claim will be verified by fact checkers.…”

Section: Conceptual Definition Of Claimmentioning

confidence: 99%

See 2 more Smart Citations

Automated fact‐checking: A survey

Zeng

Abumansour

Zubiaga

2021

Language and Linguist. Compass

View full text Add to dashboard Cite

As online false information continues to grow, automated fact‐checking has gained an increasing amount of attention in recent years. Researchers in the field of Natural Language Processing (NLP) have contributed to the task by building fact‐checking datasets, devising automated fact‐checking pipelines and proposing NLP methods to further research in the development of different components. This article reviews relevant research on automated fact‐checking covering both the claim detection and claim validation components.

show abstract

Section: Datasetsmentioning

confidence: 99%

Section: Check-worthy Claim Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Automated fact‐checking: A survey

Zeng

Abumansour

Zubiaga

2021

Language and Linguist. Compass

View full text Add to dashboard Cite

show abstract

“…ClaimRank extends this to Arabic (in addition to English) and uses a richer feature set that includes the context. Other more recent work include datasets that are bigger in size and across longer time spans or in other languages such as Dutch (Berendt et al, 2020). Covering multiple domains (political speeches, tweets, Wikipedia) and task formulations (check-worthiness, rumor detection, and citation detection), Wright and Augenstein (2020) use positive unlabelled learning (Bekker and Davis, 2020) to perform a comparison of datasets across domains where the notion of check-worthiness vary greatly.…”

Section: Related Workmentioning

confidence: 99%

Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue

2021

View full text Add to dashboard Cite

We are glad to pen the first few words for the proceedings of SIGDIAL 2021, the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue. The SIGDIAL conference is a premier publication venue for research in discourse and dialogue. This year, the conference is organized as a hybrid event with both in-person and virtual participation on July 29-31, 2021, right before ACL-IJCNLP 2021. The 2021 Young Researchers' Roundtable on Spoken Dialog Systems (YRRSDS 2021) is also held as a satellite event. The SIGDIAL 2021 program features three keynote talks, 6 paper presentation sessions, 1 demo session, and 2 special sessions, entitled "Summarization of Dialogues and Multi-Party Meetings", and "Safety for E2E Conversational AI".COVID has changed the way we work, but it doesn't hamper our research progress. We received 142 submissions this year, comprising 88 long papers, 49 short papers, and 5 demo descriptions. We had 12 Senior Program Committee (SPC) members who were each responsible for 11-12 papers, leading the discussion process and also contributing meta-reviews. Each submission was assigned to an SPC member and received at least three reviews. Decisions carefully considered the original reviews, meta-reviews, and discussions among reviewers facilitated by the SPCs. We are immensely grateful to the members of the Program Committee and Senior Program Committee for efforts in providing excellent, thoughtful reviews of the large number of submissions. Their contributions have been essential to selecting the accepted papers and providing a high-quality technical program for the conference. We have aimed to develop a broad, varied program spanning the many positively rated papers identified by the review process. We accepted 59 papers in total: 40 long papers (45%), 15 short papers (31%), and 4 demo descriptions, for an overall acceptance rate of 41.5%, in line with prior years. One keynote will highlight each of the three days of the conference. In organizing this hybrid inperson/virtual conference, we have tried to maintain as much of the spirit of a fully online conference as possible. Recordings for all papers and demos have been made available several days before the start of the conference, for participants to watch asynchronously. Long and short papers are organized into sessions taking into consideration the presenters' time zones. Regular papers sessions span 8-11 papers, each presented as a two-minute pre-recorded talk followed by five minutes of live Q&A. For demos, we organized four parallel zoom rooms to allow participants to interact with and observe live interactions with the systems. The topics represent the breadth of research in discourse and dialogue. A conference of this size requires the energy, guidance, and contributions of many parties, and we would like to take this opportunity to thank and acknowledge them all. We thank our three keynote speakers, Julia Hirschberg (Columbia University), Raymond J. Mooney (University of Texas at Austin), and Jason Weston (Facebook AI & NYU), for...

show abstract

“…As a result, the company may lose profits [6]. However, in recent years, clickbait has begun to be frequently used by cybercriminals to lure people to harmful Internet resources to steal their personal information [7]. This is a very large problem since in addition to the various viruses contained in the links [8], they can also contain executable code that can harm the user [9].…”

Section: Introductionmentioning

confidence: 99%

Blockchain-Enabled Deep Recurrent Neural Network Model for Clickbait Detection

Razaque

Alotaibi

et al. 2022

IEEE Access

View full text Add to dashboard Cite

When people use social networks, they often fall prey to a clickbait scam. The scammer attempts to create a striking headline that attracts the majority of users and attaches a link. The user follows the link and can be redirected to a fraudulent resource where the user easily loses personal data. To solve this problem, a Blockchain-enabled deep recurrent neural network (BDRNN) is proposed to detect the nature safe and malicious clickbait from the contents. The proposed BDRNN consists of three phases: analysis of clickbait and source rating, clickbait search process and multi-layered clickbait detection. The analysis of clickbait and source rating phase helps to analyze different sources to detect the clickbait and also rating the content-sources. To achieve the clickbait analysis and source rating, the detection of blacklisted/white-listed source and source rating check algorithms are introduced. The clickbait search process is accomplished by incorporating the binary search features for a faster and more efficient search process for malicious content-detection. The multi-layered clickbait detection is main phase of the proposed BDRNN that consists of three models: content-to-vector model (layer-1), deep neural network model(layer-2), and Blockchainenabled malicious content detection model (layer-3). These models collectively detect the malicious and safe clickbait from the contents. The extensive experiments are conducted to determine the effectiveness of the proposed BDRNN model and compared with the existing state-of-the-art neural network models designed for clickbait detection, and the result demonstrates that the proposed BDRNN model outperforms the counterparts from the, accuracy, link detection, memory usage, analogous perspectives, and attacker's successful content capturing rate.

show abstract

FactRank: Developing automated claim detection for Dutch-language fact-checkers

Cited by 13 publications

References 10 publications

Automated fact‐checking: A survey

Automated fact‐checking: A survey

Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue

Blockchain-Enabled Deep Recurrent Neural Network Model for Clickbait Detection

Contact Info

Product

Resources

About