ABSTRACT
With the development of social media, false news has become a serious problem facing today’s society. In view of the fact that most of the existing research on fake news detection technology relies on external knowledge sources, and there are still limitations in processing text details, this paper proposes a fake news detection algorithm (BCCU) that integrates multi-level features. First, the pre-trained model BERT is used to obtain global text features, and the BERT coding layer is used to access the capsule network to extract local text features. Then a collaborative attention mechanism is introduced to process the redundant parts of the two text features and fuse the two. Finally User attribute data is added to assist in false news detection to improve the model’s ability to predict future news. Experimental results show that when this method only relies on news text, the accuracy on Weibo, Twitter15 and Twitter16 datasets are 1.1%, 13.3% and 11.4% higher than the classic model (RvNN) respectively.
- Leo Breiman. 2017. Classification and regression trees. Routledge.Google Scholar
- Adele Cutler, D Richard Cutler, and John R Stevens. 2012. Random forests. Ensemble machine learning: Methods and applications (2012), 157–175.Google Scholar
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018).Google Scholar
- Yingtong Dou, Kai Shu, Congying Xia, Philip S Yu, and Lichao Sun. 2021. User preference-aware fake news detection. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2051–2055.Google ScholarDigital Library
- Evelyn Fix and Joseph Lawson Hodges. 1952. Discriminatory analysis: Nonparametric discrimination: Small sample performance. (1952).Google Scholar
- Zhiwei Guo, Keping Yu, Alireza Jolfaei, Gang Li, Feng Ding, and Amin Beheshti. 2022. Mixed graph neural network-based fake news detection for sustainable vehicular social networks. IEEE Transactions on Intelligent Transportation Systems (2022).Google Scholar
- Qingyuan Hu, Qian Li, Youshui Lu, Yue Yang, and Jingxian Cheng. 2022. Correction to: Multi-level word features based on CNN for fake news detection in cultural communication. Personal and Ubiquitous Computing 26, 3 (2022), 911–911.Google ScholarDigital Library
- Shengyi Jiang, Xiaoting Chen, Liming Zhang, Sutong Chen, and Haonan Liu. 2019. User-characteristic enhanced model for fake news detection in social media. In Natural Language Processing and Chinese Computing: 8th CCF International Conference, NLPCC 2019, Dunhuang, China, October 9–14, 2019, Proceedings, Part I 8. Springer, 634–646.Google ScholarDigital Library
- Yang Liu and Yi-Fang Wu. 2018. Early detection of fake news on social media through propagation path classification with recurrent and convolutional networks. In Proceedings of the AAAI conference on artificial intelligence, Vol. 32.Google ScholarCross Ref
- Yi-Ju Lu and Cheng-Te Li. 2020. GCAN: Graph-aware co-attention networks for explainable fake news detection on social media. arXiv preprint arXiv:2004.11648 (2020).Google Scholar
- Jing Ma, Wei Gao, Prasenjit Mitra, Sejeong Kwon, Bernard J Jansen, Kam-Fai Wong, and Meeyoung Cha. 2016. Detecting rumors from microblogs with recurrent neural networks. (2016).Google Scholar
- Jing Ma, Wei Gao, and Kam-Fai Wong. 2018. Rumor detection on twitter with tree-structured recursive neural networks. Association for Computational Linguistics.Google Scholar
- Jing Ma, Wei Gao, and Kam-Fai Wong. 2018. Rumor detection on twitter with tree-structured recursive neural networks. Association for Computational Linguistics.Google Scholar
- Qiong Nan, Juan Cao, Yongchun Zhu, Yanyan Wang, and Jintao Li. 2021. MDFEND: Multi-domain fake news detection. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management. 3343–3347.Google ScholarDigital Library
- Sara Sabour, Nicholas Frosst, and Geoffrey E Hinton. 2017. Dynamic routing between capsules. Advances in neural information processing systems 30 (2017).Google Scholar
- Changhe Song, Cheng Yang, Huimin Chen, Cunchao Tu, Zhiyuan Liu, and Maosong Sun. 2019. CED: credible early detection of social media rumors. IEEE Transactions on Knowledge and Data Engineering 33, 8 (2019), 3035–3047.Google ScholarCross Ref
- Vaibhav Vaibhav, Raghuram Mandyam Annasamy, and Eduard Hovy. 2019. Do sentence interactions matter? leveraging sentence level representations for fake news classification. arXiv preprint arXiv:1910.12203 (2019).Google Scholar
- Vladimir Vapnik, Steven Golowich, and Alex Smola. 1996. Support vector method for function approximation, regression estimation and signal processing. Advances in neural information processing systems 9 (1996).Google Scholar
- Yuhang Wang, Li Wang, Yanjie Yang, and Tao Lian. 2021. SemSeq4FD: Integrating global semantic relationship and local sequential order to enhance text representation for fake news detection. Expert Systems with Applications 166 (2021), 114090.Google ScholarCross Ref
- Song Z Wu S, Dong Q. 2022. A Review of Research on Detection Methods of Misinformation in Social Media. Journal of Information Science 41, 6 (2022), 651–661.Google Scholar
- Fan Yang, Yang Liu, Xiaohui Yu, and Min Yang. 2012. Automatic detection of rumor on sina weibo. In Proceedings of the ACM SIGKDD workshop on mining data semantics. 1–7.Google ScholarDigital Library
Index Terms
- Fake news detection algorithm based on incorporating multi-level features
Recommendations
Extracting Common Features of Fake News by Multi-Head-Attention
Security and Privacy in Social Networks and Big DataAbstractSeveral methods for detecting fake news using machine learning have been proposed. Previous studies have only focused on a limited dataset, and few researchers have proposed versatile models that can be applied to various fields. In this study, we ...
Multidimensional Analysis of Fake News Spreaders on Twitter
Computational Data and Social NetworksAbstractSocial media has become a tool to spread false information with the help of its large complex network. The consequences of such misinformation could be very severe. The paper uses the Twitter conversations about the scrapping of Article 370 in ...
Fake News Early Detection: A Theory-driven Model
Field NotesMassive dissemination of fake news and its potential to erode democracy has increased the demand for accurate fake news detection. Recent advancements in this area have proposed novel techniques that aim to detect fake news by exploring how it ...
Comments