计算机科学 ›› 2024, Vol. 51 ›› Issue (4): 307-313.doi: 10.11896/jsjkx.230900087
段钰潇, 胡艳丽, 郭浩, 谭真, 肖卫东
DUAN Yuxiao, HU Yanli, GUO Hao, TAN Zhen, XIAO Weidong
摘要: 近年来,随着互联网及多媒体技术的迅猛发展,人们获取信息更加方便快捷,然而虚假信息在网络上的传播也日益严重,负面影响不断扩大。为了增强信息的可信度和欺骗性,虚假信息呈现多模态发展趋势,使得检测工作面临更大挑战。现有的多模态虚假信息检测方法大多关注多模态特征的形成,对于跨模态歧义和不同模态特征在检测中的贡献率的研究尚不完善,忽略了不同模态特征间固有差异性对虚假信息检测的影响。为解决该问题,提出了构建改进的跨模态关联歧义学习的虚假信息检测模型,通过对文本和图像特征进行跨模态歧义学习,利用歧义得分更新单模态与融合特征的权重,自适应地拼接单模态与融合特征;同时采用网格搜索动态分配文本、图像特征权重,提高检测准确率。在Twitter数据集上对该模型的有效性进行验证,其相比基线模型准确率提高了6%,相比未进行动态权重分配的检测方法性能提升了1.6%。
中图分类号:
[1]JIN Z,CAO J,WANG B,et al.Research on social multimedia rumor detection technology integrating multi-modal features [J].Journal of Nanjing University of Information Science and Technology(Natural Science Edition),2017,9(6):583-592. [2]ISLAM S,SARKAR T,KHAN S H,et al.COVID-19-related infodemic and its impact on public health:A global social media analysis[J].Am.J.Trop.Med.Hyg,2020,103(4),1621-1629. [3]CAO J,SHENG Q,QI P.Progress and prospect of Internet false information detection [J].Communication of China Computer Society,2020,16(3):52-57. [4]KHATTAR D,GOND J,GUPTA M,et al.MVAE:Multimodal Variational Autoencoder for Fake News Detection[C]//The World Wide Web Conference.2019:2915-2921. [5]WANG Y Q,MA F L,JIN Z W,et al.EANN:Event Adversa-rial Neural Networks for Multi-Modal Fake News Detection[C]//ACM SIGKDD International Conference on Knowledge Discovery Data Mining(KDD).2018:849-857. [6]POPAT K,MUKHERJEE S,YATES A,et al.DeClarE:Debunking Fake News and False Claims Using Evidence-Aware Deep Learning[C]//Proceeding of the 2018 Conference on Empirical Methods in Natural Language Processing(EMNLP),Brussels,Belgium.USA:ACL.2018:22-32. [7]SONG C,SHU K,WU B.Temporally evolving graph neural network for fake news detection[J].Information Processing & Management,2021,58:102712. [8]LIU Y,WU Y F B.Early detection of fake news on social media through propagation path classifica-tion with recurrent and convolutional networks[C]//The 32th AAAI Conference on Artificial Intelligence(AAAI-18).2018:354-361. [9]XUE J,WANG Y,TIAN Y,et al.Detecting fake news by exploring the consistency of multimodal data[J].Information Processing & Management.2021,58(5):102610. [10]ZHOU X,WU J,ZAFARANI R.Safe:Similarity-aware multi-modal fake news detection[J].arXiv:2003.04981,2020. [11]ZHANG G,LI J.Detecting Social Media Fake News with Semantic Consistency Between Multi-model Contents[J].Data Analysis and Knowledge Discovery,2021,5(5):21-29. [12]SHIVANGI S,MUDIT D,RAJIV R S,et al.Inter-Modality Discordance for Multimodal Fake News Detection[C]//ACM Multimedia Asia(MMAsia'21).2021:1-7. [13]QI P,CAO J,LI X R,et al.Improving Fake News Detection by Using an Entity-enhanced Framework to Fuse Diverse Multi-modal Clues[C]//ACM MM21.2021:1212-1220. [14]QI P,CAO J,SHENG Q.Semantics-Enhanced Multi-ModalFake News Detection[J].Journal of Computer Research and Development,2021,58(7):1456-1465. [15]CHEN Y,LI D,ZHANG P,et al.Cross-modal ambiguity lear-ning for multimodal fake news detection[C]//Proceedings of the ACM Web Conference.2022:2897-2905. [16]HUA J,CUI X D,LI X H,et al.Multimodal fake news detection through data augmentation-based contrastive learning[J].Applied Soft Computing,2023,136(C):1568-4946. [17]YING Q,HU X,ZHOU Y,et al.Bootstrapping multi-view representations for fake news detection[C]//AAAI.2023. [18]BOIDIDOU C,PAPADOPOULOS S,ZAM-POGLOU M,et al.Detection and visualization of misleading content on Twitter[J].International Journal of Multimedia Information Retrieval,2018,7(1):71-86. [19]JIN Z,CAO J,GUO H,et al.Multimodal fusion with recurrent neural networks for rumor detection on microblogs[C]//Proceedings of the 25th ACM International Conference on Multimedia.2017:795-816. [20]WU Y,ZHAN P,ZHANG Y,et al.Multimodal Fusion with Co-Attention Networks for Fake News Detection[OL].https://aclanthology.org/2021.findings-acl.226/. [21]CHEN Y X,LI D S,ZHANG P,et al.Cross-modal Ambiguity Learning for Multimodal Fake News Detection[C]//Procee-dings of the ACM Web Conference 2022(WWW'22).Virtual Event,Lyon,France.ACM,New York,NY,USA,2022:2897-2905. |
|