计算机科学 ›› 2024, Vol. 51 ›› Issue (3): 14-19.doi: 10.11896/jsjkx.230800063
廖劲智1, 赵和伟1, 连小童1, 纪文亮1, 石海明1, 赵翔2
LIAO Jinzhi1, ZHAO Hewei1, LIAN Xiaotong1, JI Wenliang1, SHI Haiming1, ZHAO Xiang2
摘要： 当前,网络上充斥着大量虚假信息,严重阻碍了社会各行业的正常运转,如何精准检测虚假信息成为了亟待解决的问题。现有研究主要从账户特征、文本内容和多模态3个角度开展工作,但大多忽视了虚假信息赖以传播的关键特征(即内容新奇性),仅是孤立地分析判别目标信息的真实性,未能把握舆论环境的特征。因此,提出了一种基于对比图学习的跨文档虚假信息检测方法(Contrastive Graph Learning,CAL),聚焦于内容新奇性,主要包含两个关键模块:对比学习模块和异构图模块。前者致力于扩大客观事实与虚假信息在向量空间中的表示差异性;后者包含实体、事件、事件集、句子和文档5种类型实体,尽可能向实体表示中注入舆论环境的语义特征。最后,在IED,TL17和Crisis这3个数据集上,在文档级和事件级这两个层次上开展了相关实验,CAL在所有测试中均取得了最优的结果,验证了所提方法的有效性。
中图分类号:
| [1]SOROUSH V,ROY D,ARAL S,et al.The spread of true andfalse news online [J].Science,2018,359:1146-1151. [2]JIN Z,CAO J,ZHANG Y,et al.News verification by exploiting conflicting social viewpoints in microblogs [C]//AAAI Confe-rence on Artificial Intelligence.2016:2972-2978. [3]WU L,RAO Y,JIN H,et al.Different absorption from the same sharing:Sifted multi-task learning for fake news detection [C]//Conference on Empirical Methods in Natural Language Proce-ssing(EMNLP).2019:4643-4652. [4]TACCHINI E,BALLARIN G,VEDOVA M L,et al.Some like it hoax:Automated fake news detection in social networks [J].arXiv:1704.07506,2017. [5]YANG W,LIANG G,XIE K.Rumor detection method based on burst topic detection and domain expert discovery [J].Journal of Computer Applications,2017,37(10):2799- 2805. [6]SHU K,MAHUDESWARAN D,WANG S,et al.Fakenewsnet:A data repository with news content,social context,and spatiotemporal information for studying fake news on social media [J].Big Data,2020,8(3):171-188. [7]GUPTA M,ZHAO P,HAN J.Evaluating event credibility ontwitter [C]//International Conference on Data Mining(ICDM).2012:153-164. [8]ZHANG J,DONG B,YU P S.Fakedetector:Effective fake news detection with deep diffusive neural network [C]//International Conference on Data Engineering(ICDE).2020:1826-1829. [9]XUE H,WANG L,YANG Y,et al.Rumor detection modelbased on user propagation network and message content [J].Journal of Computer Applications,2021,41(12):3540-3545. [10]CONROY N,RUBIN V L,CHEN Y.Automatic deception detection:Methods for finding fake news [C]//Association for Information Science and Technology.2015:1-4. [11]GAO M,CHEN F.Credibility evaluating method of Chinese microblog based on information fusion [J].Journal of Computer Applications,2016,36(8):2071-2075,2081. [12]POTTHAST M,KIESEL J,REINARTZ K,et al.A stylometric inquiry into hyperpartisan and fake news [C]//Annual Meeting of the Association for Computational Linguistics(ACL).2018:231-240. [13]SITAULA N,MOHAN C K,GRYGIEL J,et al.Credibilitybased fake news detection [J].arXiv:1911.00643,2019. [14]LEE D,KIM Y,KIM H,et al.Fake News Detection Using Deep Learning [J].The Journal of Information Processing Systems,2019,15:1119-1130. [15]VAIBHAV V,ANNASAMY R M,HOVY E H.Do sentence interactions matter? leveraging sentence level representations for fake news classification [C]//Workshop on Graph-Based Me-thods for Natural Language Processing.2019:134-139. [16]PAN J Z,PAVLOVA S,LI C,et al.Content based fake news detection using knowledge graphs [C]//International Semantic Web Conference(ISWC).2018:669-683. [17]WANG H,GONG L,ZHOU Z,et al.Dis-information from Social Media with Semantic Enhancement[J].Data Analysis and Knowledge Discovery,2023,7(2):48-60. [18]SIMONYAN K,ZISSERMAN A.Very Deep Convolutional Networks for Large-Scale Image Recognition [C]//International Conference on Learning Representations(ICLR).2015. [19]WANG Y,MA F,JIN Z,et al.EANN:Event Adversarial Neural Networks for Multimodal Fake News Detection [C]//ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2018:849-857. [20]KHATTAR D,GOUD J S,GUPTA M,et al.MVAE:Multimodal Variational Autoencoder for Fake News Detection [C]//The Web Conference(WWW).2019:2915-2921. [21]SINGHAL S,SHAH R R,CHAKRABORTY T,et al.Spot-Fake:A Multi-modal Framework for Fake News Detection [C]//International Conference on Multimedia Big Data.2019:39-47. [22]WANG W Y.liar,liar pants on fire:A new benchmark dataset for fake news detection [C]//Annual Meeting of the Association for Computational Linguistics(ACL).2017:422-426. [23]ZHANG H,FANG Q,QIAN S,et al.Multimodal Knowledge-aware Event Memory Network for Social Media Rumor Detection [C]//ACM International Conference on Multimedia(MM).2019:1942-1951. [24]SONG C,NING N,ZHANG Y,et al.A Multimodal Fake News Detection Model Based on Crossmodal Attention Residual and Multichannel Convolutional Neural Networks [J].Information Process and Management(IPM),2021,58(1):102437. [25]WANG Y,QIAN S,HU J,et al.Fake News Detection viaKnowledge-Driven Multimodal Graph Convolutional Networks [C]//International Conference on Multimedia Retrieval(ICMR).2020:540-547. [26]LIU J,FENG K,JEFF Z P,et al.MSRD:Multi-Modal Web Rumor Detection Method[J].Journal of Computer Research and Development,2020,57(11):2328-2336. [27]WU X,HUANG K,FUNG Y R,et al.Cross-document Misinformation Detection based on Event Graph Reasoning [C]//North American Chapter of the Association for Computational Linguistics(NAACL).2022:543-558. [28]CHEN T,KORNBLITH S,NOROUZI M,et al.A SimpleFramework for Contrastive Learning of Visual Representations [C]//International Conference on Machine Learning(ICML).2020:1597-1607. [29]LIN Y,JI H,HUANG F,et al.A joint neural model for information extraction with global features [C]//Annual Meeting of the Association for Computational Linguistics(ACL).2020:7999-8009. [30]PAN X,ZHANG B,MAY J,et al.Cross lingual name tagging and linking for 282 languages [C]//Annual Meeting of the As sociation for Computational Linguistics(ACL).2017:1946-1958. [31]LEE K,HE L,LEWIS M,et al.End-to-end neural coreference resolution [C]//Conference on Empirical Methods in Natural Language Processing(EMNLP).2017:188-197. [32]LAI T,JI H,BUI T,et al.A context-dependent gated module for incorporating symbolic semantics into event coreference re-solution[C]//North American Chapter of the Association for Computational Linguistics:Human Language Technologies(NAACL).2021:3491-3499. [33]WEN H,LIN Y,LAI T,et al.RESIN:A dockerized schemaguided cross-document cross-lingual cross-media in formation extraction and event tracking system [C]//North American Chapter of the Association for Computational Linguistics:Human Language Technologies:Demonstrations(NAACL).2021:133-143. [34]DEVLIN J,CHANG M,LEE K,et al.BERT:pre-training of deep bidirectional transformers for language understanding [C]//North American Chapter of the Association for Computational Linguistics:Human Language Technologies(NAACL).2019:4171-4186. [35]HAMILTON W L,YING Z,LESKOVEC J.Inductive representation learning on large graphs [C]//Annual Conference on Neural Information Processing Systems(NeurIPS).2017:1024-1034. [36]KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks [C]//International Conference on Learning Representations(ICLR).2017. [37]SRIVASTAVA R K,GREFF K,SCHMIDHUBER J.Highway Networks[J].arXiv:1505.00387,2015. [38]BORDES A,USUNIER N,GARCÌA-DURÁN A,et al.Translating embeddings for modeling multi-relational data [C]//Neural Information Processing Systems(NeurIPS).2013:2787-2795. [39]LI M,LI S,WANG Z,et al.Future is not one-dimensional:Graph modeling based complex event schema induction for event prediction [J].arXiv:2104.06344,2021. [40]TRAN G B,ALRIFAI M,NGUYEN D Q.Predicting relevant news events for timeline summaries [C]//International World Wide Web Conference(WWW).2013:91-92. [41]KARIMI H,TANG J.Learning hierarchical discourse-levelstructure for fake news detection [C]//North American Chapter of the Association for Computational Linguistics:Human Language Technologies(NAACL).2019:3432-3442. [42]ZELLERS R,HOLTZMAN A,RASHKIN H,et al.Defending against neural fake news [C]//Neural Information Processing Systems(NeurIPS).2019:9051-9062. |
|
||
首页