虚假新闻的大量传播对个人和社会都造成巨大的危害,通过智能算法检测虚假新闻是阻止虚假新闻传播的重要途径。针对不同语境中虚假新闻检测不准确的问题,该文将新闻的背景事实特征和新闻的风格特征融入到模型中,可以提高模型解决缺少背景知识的虚假新闻检测能力,增强模型的鲁棒性,其中新闻的风格包括情感风格和文本风格。同时该文构建了多通道融合器融合新闻与背景知识的差异性特征,语义特征和风格特征,组成了基于事实和风格的虚假新闻检测框架FSFD。在CHEF中文开放数据集上的实验证明,该文提出的检测方法在F1值上比基准模型提升了2.3%,可见,该文方法适用于背景丰富的新闻,为在线社交媒体的虚假新闻检测提供有力支持。
Abstract
The widespread dissemination of fake news poses significant harm to individuals and society. To detect fake news in different contexts, this paper incorporates the background factual features and stylistic features of news into the model. This integration enhances the model's ability to detect fake news lacking background knowledge and improves its robustness. The stylistic features include emotional style and textual style. Additionally, this paper constructs a multi-channel integrator that combines differential features of news and background knowledge, semantic features, and stylistic features, forming the FSFD framework. Validation using the CHEF Chinese open dataset demonstrates that the proposed method outperforms the baseline model by 2.3% in terms of F1 score.
关键词
虚假新闻检测 /
证据检索 /
多通道融合 /
预训练模型
{{custom_keyword}} /
Key words
fake news detection /
evidence retrieval /
multi-channel fusion /
pre-trained model
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 高玉君,梁刚,蒋方婷,等.社会网络谣言检测综述[J]. 电子学报,2020,48(07): 1421-1435.
[2] CUI L, SHU K, WANG S, et al. DEFEND: A system for explainable fake news detection[C]//Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 2019: 2961-2964.
[3] SHENG Q, CAO J, ZHANG X, et al. Zoom out and observe: News environment perception for fake news detection[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, 2022: 4543-4556.
[4] CONROY N, RUBIN V, CHEN Y. Automatic deception detection: Methods for finding fake news[C]//Proceedings of the Association for Information Science and Technology,2015: 1-4.
[5] HORNE B, ADALI S. This just in: Fake news packs a lot in title, uses simpler, repetitive content in text body, more similar to satire than real news[C]//Proceedings of the International AAAI Conference on Web andSocial Media, 2017: 759-766.
[6] 刘赏,沈逸凡. 基于新闻标题-正文差异性的虚假新闻检测方法[J]. 数据分析与知识发现,2022,7(2): 1-16.
[7] PRZYBYLA P. Capturing the style of fake news[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 490-497.
[8] CHOY M, CHONG M. Seeing through misinformation: A framework for identifying fake online news[J].arXiv preprint arXiv:1804.03508,2018.
[9] WU S, TAN C, KLEINBERG J, et al. Does bad news go away faster?[C]//Proceedings of the 5th International Conference on Weblogs and Social Media, 2011,5(1): 646-649.
[10] GOLBECK J, MAURIELLO M, AUXIER B, et al. Fake news vs satire: A dataset and analysis.[C]//Proceedings of the the 10th ACM Conference on Web Science, 2018: 17-21.
[11] DOSHI A, RAGHAVAN S, SCHMIDT W. Real-time prediction of online false information purveyors and their characteristics[J/OL].InfoSciRN: Machine Learning (Sub-Topic),2020. https://dx.doi.org/10.2139/ssrn.3725919.
[12] SONG C, SHU K, WU B. Temporally evolving graph neural network for fake news detection[J].Information Processing and Management,2021,58(6): 102712.
[13] SHAHBAZI Z, BYUN Y. Fake media detection based on natural language processing and block chain approaches[J].IEEE Access,2021(9): 128442-128453.
[14] GOLDANI M, MOMTAZI S, SAFABAKHSH R. Detecting fake news with capsule neural networks[J]. Applied Soft Computing, 2021(101): 106991.
[15] MONTI F, FRASCA F, EYNARD D, et al. Fake news detection on social media using geometric deep learning[J]. arXiv preprint arXiv:1902.06673,2019.
[16] SHENG Q, ZHANG X, CAO J, et al. Integrating pattern-and fact-based fake news detection via model preference learning[C]//Proceedings of the 30th ACM International Conference on Information and Knowledge Management,2021: 1640-1650.
[17] WANG Y, QIAN S, HU J, et al. Fake news detection via knowledge-driven multimodal graph convolutional networks[C]//Proceedings of the International Conference on Multimedia Retrieval,2020: 540-547.
[18] VO N, LEE K. Hierarchical multi-head attentive network for evidence-aware fake news detection[C]//Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics,2021: 965-975.
[19] POPAT K, MUKHERJEE S, STRTGEN J, et al. Where the truth lies: Explaining the credibility of emerging claims on the web and social media[C]//Proceedings of the 26th International Conference on World Wide Web Companion,2017: 1003-1012.
[20] SHENG Q, CAO J, ZHANG X, et al. Article reranking by memory-enhanced key sentence matching for detecting previously fact-checked claims[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing,2021: 5468-5481.
[21] ROBERTSON S, ZARAGOZA H. The probabilistic relevance framework: BM25 and beyond[J]. Foundations and Trends in Information Retrieval,2009,3(4): 333-389.
[22] LIN C. Rouge: A package for automatic evaluation of summaries[G]//Text Summarization Branches Out,2004: 74-81.
[23] KIM Y. Convolutional neural networks for sentence classification[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics,2014: 1746-1751.
[24] ZHANG X, CAO J, LI X, et al. Mining dual emotion for fake news detection[C]//Proceedings of the Web Conference,2021: 3465-3476.
[25] DONG Z, DONG Q.HowNet: A hybrid language and knowledge resource[C]//Proceedings of International Conference on Natural Language Processing and Knowledge Engineering, 2003: 820-824.
[26] BIRD S, KLEIN E, LOPER E. Natural language processing with Python: Analyzing text with the natural language toolkit[J]. Language Resources and Evaluation,2010,44(4): 421-424.
[27] ZHU Y, SHENG Q, CAO J, et al. Memory-guidedmulti-view multi-domain fake news detection[J]. IEEE Transactions on Knowledge and Data Engineering,2022,35(7): 7178-7191.
[28] HU X, GUO Z, WU G, et al. CHEF: A pilot Chinese dataset for evidence-based fact-checking[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,2022: 3362-3376.
[29] ZHOU J, HAN X, YANG C, et al. GEAR: Graph-based evidence aggregating and reasoning for fact verification[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics,2019: 892-901.
[30] RAI N, KUMAR D, KAUSHIK N, et al. Fake news classification using transformer based enhanced LSTM and BERT[J]. International Journal of Cognitive Computing in Engineering, 2022(3): 98-105.
[31] POPAT K, MUKHERJEE S, YATES A, et al. Declare: Debunking fake news and false claims using evidence-aware deep learning[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing,2018: 22-32.
[32] SUN Y, CHENG Y, GAN J, et al. ERNIE: Enhanced language representation with informative entities[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019:1441-1451.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
河南省高等学校重点科研项目(22B520054);嵩山实验室预研项目(YYJC032022021);中原工学院自然科学基金(K2023MS021)
{{custom_fund}}