Contextual Target-Specific Stance Detection on Twitter: Dataset and Method DOI
Yupeng Li, Dacheng Wen, Haorui He

et al.

2021 IEEE International Conference on Data Mining (ICDM), Journal Year: 2023, Volume and Issue: unknown, P. 359 - 367

Published: Dec. 1, 2023

To understand different aspects of online human behaviors, e.g., the public stances toward various social and political issues, contextual target-specific stance detection has become one most important studies on media. Considering lack appropriate data for Twitter, which is popular platforms worldwide, we introduce CTSDT, a new dataset that consists large number annotated conversations collected from Twitter. Furthermore, propose model called ConMulAttn, first method can learn both contents posts concrete relationships between in conversation. We conduct extensive evaluation using CTSDT as well another two datasets, CreateDebate ConvinceMe, detection. The results validate necessity introducing our CTSDT. Besides, according to results, proposed ConMulAttn outperform state-of-the-art by up 25% F 1 score, indicating effectiveness superiority solution. Our study potential assist policymakers utilizing conversation efficiently gain real-time insights into target topics, such vaccination.

Language: Английский

Not all fake news is semantically similar: Contextual semantic representation learning for multimodal fake news detection DOI Open Access
Liwen Peng, Songlei Jian, Zhigang Kan

et al.

Information Processing & Management, Journal Year: 2023, Volume and Issue: 61(1), P. 103564 - 103564

Published: Oct. 31, 2023

Language: Английский

Citations

28
Classification and Detection of Rumors Related to COVID-19 Using Machine Learning-Based Smart Techniques DOI Creative Commons
Yancheng Yang, Jintao Zhai, Shah Nazir

et al.

SAGE Open, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 1, 2025

The COVID-19 coronavirus pandemic, a serious health risk, has affected information-related behavior and led to an upsurge in rumor-sharing on social media. Thus, combating necessitates rumors as well, which serves compelling incentive examine rumor-related during this unusual period. analysis of the prior literature was summarized current study. For this, number well-known libraries were searched, including ScienceDirect, Springer, ACM, IEEE Explore. proposed research is based detailed overview detection recognition different deceptive news about pandemic using various ML algorithms. It found that with implementation approach, it efficient perform classification information into real fake media platforms. After studying techniques, features have been identified from literature. Then, important extracted used process ranking. effective categorization available alternatives, Graph Theory Matrix Approach used. alternatives are ranked their permanent function values. study considered providing comprehensive data currently available. demonstrates many methods for analyzing literature, enabling students create fresh perspectives topic.

Language: Английский

Citations

0
DSMM: A dual stance-aware multi-task model for rumour veracity on social networks DOI Open Access
Guanghui Ma, Chunming Hu, Ling Ge

et al.

Information Processing & Management, Journal Year: 2023, Volume and Issue: 61(1), P. 103528 - 103528

Published: Oct. 17, 2023

Language: Английский

Citations

9
FMC: Multimodal fake news detection based on multi-granularity feature fusion and contrastive learning DOI Creative Commons
Facheng Yan, Mingshu Zhang, Bin Wei

et al.

Alexandria Engineering Journal, Journal Year: 2024, Volume and Issue: 109, P. 376 - 393

Published: Sept. 10, 2024

Language: Английский

Citations

2
Predicting and analyzing the popularity of false rumors in Weibo DOI Creative Commons

Yida Mu,

Pu Niu,

Kalina Bontcheva

et al.

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 243, P. 122791 - 122791

Published: Dec. 1, 2023

Malicious online rumors with high popularity, if left undetected, can spread very quickly damaging societal implications. The development of reliable computational methods for early prediction the popularity false is much needed, as a complement to related work on automated rumor detection and fact-checking. Besides, detecting higher in stage allows social media platforms timely deliver fact-checking information end users. To this end, we (1) propose new regression task predict future given both post user-level information; (2) introduce publicly available dataset Chinese that includes 19,256 cases from Weibo, corresponding profile original spreaders score function shares, replies reports it has received; (3) develop open-source domain adapted pre-trained language model, i.e., BERT-Weibo-Rumor evaluate its performance against several supervised classifiers using information. Our best performing model (KG-Fusion) achieves lowest RMSE (1.54) highest Pearson's r (0.636), outperforming competitive baselines by leveraging textual user profile. analysis unveils popular consist more conjunctions punctuation marks, while less contain words context personal pronouns. available: https://github.com/YIDAMU/Weibo_Rumor_Popularity.

Language: Английский

Citations

3
PANACEA: An Automated Misinformation Detection System on COVID-19 DOI Creative Commons
Runcong Zhao,

M. Arana-Catania,

Lixing Zhu

et al.

Published: Jan. 1, 2023

Runcong Zhao, Miguel Arana-catania, Lixing Zhu, Elena Kochkina, Lin Gui, Arkaitz Zubiaga, Rob Procter, Maria Liakata, Yulan He. Proceedings of the 17th Conference European Chapter Association for Computational Linguistics: System Demonstrations. 2023.

Language: Английский

Citations

2
SSRI-Net: Subthreads Stance–Rumor Interaction Network for rumor verification DOI
Zhendong Chen, Siu Cheung Hui, Lejian Liao

et al.

Neurocomputing, Journal Year: 2024, Volume and Issue: 583, P. 127549 - 127549

Published: March 13, 2024

Language: Английский

Citations

0
Transformer-based models for combating rumours on microblogging platforms: a review DOI Creative Commons
Rini Anggrainingsih, Ghulam Mubashar Hassan, Amitava Datta

et al.

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 57(8)

Published: July 20, 2024

Abstract The remarkable success of Transformer-based embeddings in natural language tasks has sparked interest among researchers applying them to classify rumours on social media, particularly microblogging platforms. Unlike traditional word embedding methods, Transformers excel at capturing a word’s contextual meaning by considering words from both the left and right word, resulting superior text representations ideal for like rumour detection This survey aims provide thorough well-organized overview analysis existing research implementing models scope this study is offer comprehensive understanding topic systematically examining organizing literature. We start discussing fundamental reasons significance automating Emphasizing critical role converting textual data into numerical representations, we review current approaches implement Transformer Furthermore, present novel taxonomy that covers wide array techniques employed deployment identifying misinformation Additionally, highlight challenges associated with field propose potential avenues future research. Drawing insights surveyed articles, anticipate promising results will continue emerge as outlined are addressed. hope our efforts stimulate further harnessing capabilities combat spread

Language: Английский

Citations

0
Resolving Unseen Rumors with Retrieval-Augmented Large Language Models DOI
Lei Chen, Zhongyu Wei

Lecture notes in computer science, Journal Year: 2024, Volume and Issue: unknown, P. 319 - 332

Published: Oct. 31, 2024

Language: Английский

Citations

0
Safe-Gta: Semantics Augmentations-Based Multi-Modal Fake News Detection Via Global-Tokens Attention DOI
Chaowei Zhang

Published: Jan. 1, 2024

Language: Английский

Citations

0