Abstract
The widespread of rumors has a negative impact on society, and rumor detection has attracted significant attention. When a new event appears, the scarcity of corresponding labeled data causes a severe challenge to rumor detection. It is necessary to query high-quality unlabeled data and annotate it for detection. Previous studies on active learning for rumor detection can query the unlabeled samples on the decision boundary based on the textual features of posts. These studies, when selecting the optimal samples, have not sufficiently considered that new event posts are usually far from old events and differ in terms of sentiment, which often plays a key role in rumor detection. Therefore, overlooking these characteristics could potentially lead to sub-optimal performance in rumor detection based on these active learning methods. To this end, we propose domain adversarial active learning based on dual features (DAAL) for rumor detection, considering these characteristics. Specifically, we first extract dual features, including affective and textual features, to obtain representations of the posts. We then propose a new active learning method that selects the samples furthest from all labeled samples based on their dual features. This method helps our rumor detection model gain more labels from new, distant event posts for training. Finally, we introduce adversarial domain training, a method designed to extract transferable features across different events (or domains), to enhance the adaptability of our rumor detection model to new events. Experimental results demonstrate DAAL can select high-quality candidates and achieve superior performance compared to existing methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wang, J., et al.: Robustness analysis of triangle relations attack in social recommender systems. In: 2020 IEEE CLOUD, pp. 557–565. IEEE (2020)
Vosoughi, S., Roy, D., Aral, S.: The spread of true and false news online. Science 359(6380), 1146–1151 (2018)
Huang, Y., Gao, M., Wang, J., Shu, K.: DAFD: domain adaptation framework for fake news detection. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds.) ICONIP 2021. LNCS, vol. 13108, pp. 305–316. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-92185-9_25
Lee, H.-Y., Li, S.-W., et al.: Meta learning for natural language processing: a survey. arXiv preprint arXiv:2205.01500 (2022)
Ghanem, B., et al.: Fakeflow: fake news detection by modeling the flow of affective information. arXiv preprint arXiv:2101.09810 (2021)
Miao, X., Rao, D., Jiang, Z.: Syntax and sentiment enhanced BERT for earliest rumor detection. In: Wang, L., Feng, Y., Hong, Yu., He, R. (eds.) NLPCC 2021. LNCS (LNAI), vol. 13028, pp. 570–582. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-88480-2_45
Dong, S., Qian, Z., Li, P., Zhu, X., Zhu, Q.: Rumor detection on hierarchical attention network with user and sentiment information. In: Zhu, X., Zhang, M., Hong, Yu., He, R. (eds.) NLPCC 2020. LNCS (LNAI), vol. 12431, pp. 366–377. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-60457-8_30
Kwon, S., et al.: Prominent features of rumor propagation in online social media. In: 2013 IEEE 13th International Conference on Data Mining, pp. 1103–1108. IEEE (2013)
Wang, Y., et al.: EANN: event adversarial neural networks for multi-modal fake news detection. In: KDD, pp. 849–857 (2018)
Gao, J., et al.: RP-DNN: a tweet level propagation context based deep neural networks for early rumor detection in social media. arXiv preprint arXiv:2002.12683 (2020)
Wang, J., et al.: Instance-guided multi-modal fake news detection with dynamic intra-and inter-modality fusion. In: PAKDD 2022, Chengdu, 16–19 May 2022, Proceedings, Part I, pp. 510–521. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-05933-9_40
Mayank, M., et al.: Deap-faked: knowledge graph based approach for fake news detection. In: ASONAM, pp. 47–51. IEEE (2022)
Ren, Y., et al.: Adversarial active learning based heterogeneous graph neural network for fake news detection. In: ICDM, pp. 452–461. IEEE (2020)
Farinneya, P., et al.: Active learning for rumor identification on social media. EMNLP 2021, 4556–4565 (2021)
Su, J.-C., et al.: Active adversarial domain adaptation. In: WACV, pp. 739–748 (2020)
Xie, B., et al.: Active learning for domain adaptation: an energy-based approach. AAAI 36, 8708–8716 (2022)
Devlin, J., et al.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: ICML, pp. 1180–1189. PMLR (2015)
Zubiaga, A., Liakata, M., Procter, R.: Exploiting context for rumour detection in social media. In: Ciampaglia, G.L., Mashhadi, A., Yasseri, T. (eds.) SocInfo 2017. LNCS, vol. 10539, pp. 109–123. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-67217-5_8
Sharma, M., Bilgic, M.: Evidence-based uncertainty sampling for active learning. Data Min. Knowl. Disc. 31, 164–202 (2017)
Sener, O., Savarese, S.: Active learning for convolutional neural networks: a core-set approach. arXiv preprint arXiv:1708.00489 (2017)
Fu, B., et al.: Transferable query selection for active domain adaptation. In: Proceedings of the CVPR, pp. 7272–7281 (2021)
Silva, A., Luo, L., Karunasekera, S., Leckie, C.: Embracing domain differences in fake news: cross-domain fake news detection using multi-modal data. AAAI 35, 557–565 (2021)
Nan, Q., Cao, J., Zhu, Y., Wang, Y., Li, J.: Mdfend: multi-domain fake news detection. In: CIKM, pp. 3343–3347 (2021)
Acknowledgements
This work was supported by the National Natural Science Foundation of China (62176028) and the Overseas Returnees Innovation and Entrepreneurship Support Program of Chongqing (cx2020097).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, C., Gao, M., Huang, Y., Jiang, F., Wang, J., Wen, J. (2023). DAAL: Domain Adversarial Active Learning Based on Dual Features for Rumor Detection. In: Liu, F., Duan, N., Xu, Q., Hong, Y. (eds) Natural Language Processing and Chinese Computing. NLPCC 2023. Lecture Notes in Computer Science(), vol 14303. Springer, Cham. https://doi.org/10.1007/978-3-031-44696-2_54
Download citation
DOI: https://doi.org/10.1007/978-3-031-44696-2_54
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44695-5
Online ISBN: 978-3-031-44696-2
eBook Packages: Computer ScienceComputer Science (R0)