Unverified Rumor Detection
Open Access
- 28 April 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 75635-75647
Abstract
Currently, early rumor detection has garnered significant attention due to the rapid dissemination of information on social media. Many existing studies approach rumor detection as a traditional classification task, disregarding the existence of unverified rumors that require future verification. To address this limitation, we present T3-ERD, a novel framework that employs an improved BigBird transformer-based model for detecting rumors of specific types while concurrently leveraging reinforcement learning to determine early time checkpoints and categorize unverified rumors. And we introduce a novel bucket strategy, Online Dynamic, which dynamically clusters comments and processes them in batches, demonstrating remarkable effectiveness. The T3-ERD achieves F1 score, accuracy, and early rate of 0.830, 0.837, and 0.220 on the Twitter15 dataset, and 0.837, 0.844, and 0.205 on the Twitter16 dataset, respectively.Keywords
This publication has 41 references indexed in Scilit:
- A model for early rumor detection base on topic-derived domain compensation and multi-user associationExpert Systems with Applications, 2024
- Enhancing large language model capabilities for rumor detection with Knowledge-Powered PromptingEngineering Applications of Artificial Intelligence, 2024
- A graph-based pivotal semantic mining framework for rumor detectionEngineering Applications of Artificial Intelligence, 2022
- A novel rumor detection with multi-objective loss functions in online social networksExpert Systems with Applications, 2022
- Dynamic graph neural network for fake news detectionNeurocomputing, 2022
- MDMN: Multi-task and Domain Adaptation based Multi-modal Network for early rumor detectionExpert Systems with Applications, 2022
- Rule-based space characterization for rumour detection in healthEngineering Applications of Artificial Intelligence, 2021
- BCMM: A novel post-based augmentation representation for early rumour detection on social mediaPattern Recognition, 2021
- A survey on fake news and rumour detection techniquesInformation Sciences, 2019
- On Early-Stage Debunking Rumors on Twitter: Leveraging the Wisdom of Weak Learners2017