Towards low-resource rumor detection: Unified contrastive transfer with propagation structure

• Main Authors: LIN, Hongzhan, MA, Jing, YANG, Ruichao, YANG, Zhiwei, CHENG, Mingfei
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Contrastive learning; Few-shot transfer; Low resource; Propagation structure; Rumor detection; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/8731; https://ink.library.smu.edu.sg/context/sis_research/article/9734/viewcontent/Low_resourceRumourDetection_av.pdf
• Institution: Singapore Management University

The truth is significantly hampered by massive rumors that spread along with breaking news or popular topics. Since there is sufficient corpus gathered from the same domain for model training, existing rumor detection algorithms show promising performance on yesterday's news. However, due to a lack of substantial training data and prior expert knowledge, they are poor at spotting rumors concerning unforeseen events, especially those propagated in different languages (i.e., low-resource regimes). In this paper, we propose a simple yet effective framework with unified contrastive transfer learning, to detect rumors by adapting the features learned from well-resourced rumor data to that of the low-resourced with only few-shot annotations. More specifically, we first represent rumor circulated on social media as an undirected topology for enhancing the interaction of user opinions, and then train the propagation-structured model via a unified contrastive paradigm to mine effective clues simultaneously from both post semantics and propagation structure. Our model explicitly breaks the barriers of the domain and/or language issues, via language alignment and a novel domain-adaptive contrastive learning mechanism. To well-generalize the representation learning using a small set of annotated target events, we reveal that rumor-indicative signal is closely correlated with the uniformity of the distribution of these events. We design a target-wise contrastive training mechanism with three event-level data augmentation strategies, capable of unifying the representations by distinguishing target events. Extensive experiments conducted on four low-resource datasets collected from real-world microblog platforms demonstrate that our framework achieves much better performance than state-of-the-art methods and exhibits a superior capacity for detecting rumors at early stages.