[1]陈开阳,徐 凡*,王明文.基于知识图谱和图像描述的虚假新闻检测研究[J].江西师范大学学报(自然科学版),2021,(04):398-402.[doi:10.16357/j.cnki.issn1000-5862.2021.04.12]
 CHEN Kaiyang,XU Fan*,WANG Mingwen.The Fake News Detection Based on Knowledge Graph and Image Description[J].Journal of Jiangxi Normal University:Natural Science Edition,2021,(04):398-402.[doi:10.16357/j.cnki.issn1000-5862.2021.04.12]
点击复制

基于知识图谱和图像描述的虚假新闻检测研究()
分享到:

《江西师范大学学报》(自然科学版)[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2021年04期
页码:
398-402
栏目:
信息科学与技术
出版日期:
2021-08-10

文章信息/Info

Title:
The Fake News Detection Based on Knowledge Graph and Image Description
文章编号:
1000-5862(2021)04-0398-05
作者:
陈开阳徐 凡*王明文
江西师范大学计算机信息工程学院,江西 南昌 330022
Author(s):
CHEN KaiyangXU Fan*WANG Mingwen
School of Computer Information Engineering,Jiangxi Normal University,Nanchang Jiangxi 330022,China
关键词:
虚假新闻 知识图谱 图像描述 Bert
Keywords:
fake news knowledge graph image caption Bert
分类号:
TP 311
DOI:
10.16357/j.cnki.issn1000-5862.2021.04.12
文献标志码:
A
摘要:
针对传统虚假新闻检测方法主要采用图像统计学和图像分布式表示特征导致没有深层次挖掘图像所表达的文字含义的问题,设计了在融合知识图谱和图像描述的深度学习下的多模态虚假新闻检测模型.该模型一方面抽取出在新闻文本中的3元组形式知识图谱,另一方面生成图像对应的描述文本,同时采用Bert框架将原文本、3元组、图像描述文本加以集成.在基准汉语虚假新闻语料库上的实验结果表明:该模型显著优于传统的代表性方法.
Abstract:
Traditional fake news detection methods mainly use image statistics and image distributed representation features without analyzing the deep semantic meaning of the text expressed behind the image.Based on this observation,the combined model which can integrate knowledge graph and image caption to detect multi-modal fake news is designed.One the one hand,the model can extract triple-style knowledge graph from the texts.On the other hand,the model can generate text description for the images.Meanwhile,the model can successfully integrate the semantic representation of source texts,triples, and image caption.Experimental results on the benchmark Chinese fake news corpus show that the model is significantly better than the representative methods.

参考文献/References:

[1] Hunt A,Matthew G.Social media and fake news in the 2016 election [J].Journal of Economic Perspectives,2017,31(2):211-236.
[2] Shao Chengcheng,Giovanni L C,Onur V,et al.The spread of fake news by social bots [EB/OL].[2020-05-13].https://arxiv.org/pdf/1707.07592.pdf.
[3] Liu Xiaomo,Armineh N,Li Quanzhi,et al.Real-time rumor debunking on twitter [EB/OL].[2020-06-15].https://dl.acm.org/doi/10.1145/2806416.2806651.
[4] Li Jiwei,Myle O,Claire C,et al.Towards a general rule for identifying deceptive opinion spam [EB/OL].[2020-06-18].http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.661.946&rep=rep1&type=pdf.
[5] Carlos C,Marcelo M,Barbara P.2011.Information credibility on twitter [EB/OL].[2020-06-15].https://doi.org/10.1145/1963405.1963500.
[6] Sejeong K,Meeyoung C,Kyomin J,et al.Prominent features of rumor propagation in online social media [EB/OL].[2020-06-19].https://ieeexplore.ieee.org/document/6729605.
[7] Wu Ke,Yang Song,Kenny Q.False rumors detection on sinaweibo by propagation structures [EB/OL].[2020-07-15].https://ieeexplore.ieee.org/document/7113322.
[8] Ma Jing,Gao Wei,Wong K F.Detect rumors in microblog posts using propagation structure via kernel learning [EB/OL].[2020-07-15].https://aclanthology.org/P17-1066.pdf.
[9] Yang Shuo,Shu Kai,Wang Suhang,et al.Unsupervised fake news detection on social media:a generative approach [EB/OL].[2020-07-15].http://www.public.asu.edu/~skai2/files/aaai_2019_unsupervised.pdf.
[10] Jin Zhiwei,Cao Juan,Guo Han,et al.Multimodal fusion with recurrent neural networks for rumor detection on microblogs [EB/OL].[2020-07-15].https://dl.acm.org/doi/10.1145/3123266.3123454.
[11] Wang Yaqing,Ma Fenglong,Jin Zhiwei,et al.Eann:event adversarial neural networks for multi-modal fake news detection [EB/OL].[2020-07-15].https://www.pianshen.com/article/57871580780/.
[12] Zlatkova D,Nakov P,Koychev I.Fact-checking meets fauxtography:verifying claims about images [EB/OL].[2020-07-15].https://arxiv.org/abs/1908.11722.
[13] Antoine B,Nicolas U,Alberto G D,et al.Translating embeddings for modeling multi relational data [EB/OL].[2020-07-15].https://dl.acm.org/doi/10.5555/2999792.2999923.
[14] Vinyals O,Toshev A,Bengio S,et al.Show and tell:a neural image caption generator [EB/OL].[2020-07-15].https://ieeexplore.ieee.org/document/7298935.
[15] Yoon Kim.Convolutional neural networks for sentence classification [EB/OL].[2020-07-15].https://arxiv.org/abs/1408.5882.
[16] Lai Siwei,Xu Liheng,Liu Kang,et al.Recurrent convolutional neural networks for text classification [EB/OL].[2020-07-15].https://ieeexplore.ieee.org/document/8852406.
[17] Armand J,Edouard G,Piotr B,et al.Bag of tricks for efficient text classification [EB/OL].[2020-07-15].https://arxiv.org/abs/1607.01759.
[18] Qi Peng,Cao Juan,Yang Tianyun,et al.Exploiting multi-domain visual information for fake news detection [EB/OL].[2020-07-15].https://arxiv.org/abs/1908.04472v1.
[19] Li Yuezun,LüSiwei.Exposing deepfake videos by detecting face warping artifacts [EB/OL].[2020-07-15].https://arxiv.org/abs/1811.00656v3.
[20] Cao Juan,Sheng Qiang,Qi Peng,et al.False news detection on social media [EB/OL].[2020-07-15].https://arxiv.org/abs/1908.10818.
[21] 刘知远,张乐,涂存超,等.中文社交媒体谣言统计语义分析 [J].中国科学:信息科学,2015,45(12):1536-1546.
[22] 王志宏,过弋.微博谣言事件自动检测研究 [J].中文信息学报,2019,33(6):132-140.

相似文献/References:

[1]冯 祥,杨庆红*.结合知识图谱进行信息强化的协同过滤算法[J].江西师范大学学报(自然科学版),2022,(04):386.[doi:10.16357/j.cnki.issn1000-5862.2022.04.09]
 FENG Xiang,YANG Qinghong*.The Collaborative Filtering Algorithm for Information Enhancement Combined with Knowledge Graph[J].Journal of Jiangxi Normal University:Natural Science Edition,2022,(04):386.[doi:10.16357/j.cnki.issn1000-5862.2022.04.09]

备注/Memo

备注/Memo:
收稿日期:2021-01-25
基金项目:国家自然科学基金(61772246,61876074,62162031)和江西省自然科学基金(20192ACBL21030)资助项目.
通信作者:徐 凡(1979—),男,江西万年人,副教授,博士,主要从事自然语言处理和语音信号处理的研究.E-mail:xufan@jxnu.edu.cn
更新日期/Last Update: 2021-08-10