[Objective] This paper proposes a multi-perspective evidence fusion model for identifying fake news, aiming to address the issues of lacking evidence and inaccurate classification in traditional model. [Methods] With the help of subjective logical model and uncertainty measurements for the classification from different perspectives, we modified the Dempster-Shafer evidence theory. Then, we used different weights to combine the evidence from multiple perspectives, and obtained the uncertainty measurements of the overall evidence and classification. [Results] We examined our model with two public data sets, and found its accuracy and F1 values were significantly higher than the traditional models. [Limitations] Evidence fusion from multiple perspectives generated some noise, which might reduce the accuracy of the results. [Conclusions] Multi-perspective evidence fusion could effectively identify fake news.
( Wu Wanpei. Research and Application of Active Learning Algorithm for Fake News Recognition[D]. Beijing: Beijing Jiaotong University, 2020.)
[2]
Shu K, Sliva A, Wang S H, et al. Fake News Detection on Social Media[J]. ACM SIGKDD Explorations Newsletter, 2017, 19(1):22-36.
doi: 10.1145/3137597.3137600
[3]
Gravanis G, Vakali A, Diamantaras K, et al. Behind the Cues: A Benchmarking Study for Fake News Detection[J]. Expert Systems with Applications, 2019, 128:201-213.
doi: 10.1016/j.eswa.2019.03.036
[4]
Lukasik M, Bontcheva K, Cohn T, et al. Gaussian Processes for Rumour Stance Classification in Social Media[J]. ACM Transactions on Information Systems, 2019, 37(2): Article No.20.
[5]
Sa A, Hinkelmann K, Corradini F. Combining Machine Learning with Knowledge Engineering to Detect Fake News in Social Networks: A Survey[C]// Proceedings of the AAAI 2019 Spring Symposium on Combining Machine Learning with Knowledge Engineering. 2019.
[6]
O’Brien N, Latessa S, Evangelopoulos G, et al. The Language of Fake News: Opening the Black-Box of Deep Learning Based Detectors[C]// Proceedings of the 32nd Conference on Neural Information Processing Systems. 2018.
[7]
Ren Y C, Xing T, Xing Z F, et al. Design on Data Manipulation Class Based on ADO.NET[J]. Applied Mechanics and Materials, 2011, 109:603-607.
doi: 10.4028/www.scientific.net/AMM.109.603
[8]
Tian Y L, Krishnan D, Isola P. Contrastive Multiview Coding[C]// Proceedings of European Conference on Computer Vision. 2020:776-794.
[9]
Wang X, Kumar D, Thome N, et al. Recipe Recognition with Large Multimodal Food Dataset[C]// Proceedings of 2015 IEEE International Conference on Multimedia & Expo Workshops. 2015: 1-6.
[10]
Zhang C Q, Han Z B, Fu H Z, et al. CPM-Nets: Cross Partial Multi-View Networks[C]// Proceedings of the 33rd Conference on Advances in Neural Information Processing Systems. 2019: 559-569.
[11]
MacKay D J C. A Practical Bayesian Framework for Backpropagation Networks[J]. Neural Computation, 1992, 4(3):448-472.
doi: 10.1162/neco.1992.4.3.448
[12]
Gal Y, Ghahramani Z. Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning[OL]. arXiv Preprint, arXiv: 1506.02142.
[13]
Sensoy M, Kaplan K, Kandemir M. Evidential Deep Learning to Quantify Classification Uncertainty[C]// Proceedings of the 32nd International Conference on Advances in Neural Information Processing Systems. 2018: 3179-3189.
[14]
Wang W R, Arora R, Livescu K, et al. On Deep Multi-View Representation Learning[C]// Proceedings of the 32nd International Conference on International Conference on Machine Learning. 2015: 1083-1092.
[15]
Wang W R, Yan X C, Lee H, et al. Deep Variational Canonical Correlation Analysis[OL]. arXiv Preprint, arXiv:1610.03454.
[16]
Zhang H, Patel V M, Chellappa R. Hierarchical Multimodal Metric Learning for Multimodal Classification[C]// Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. 2017: 3057-3065.
[17]
Dempster A P. Upper and Lower Probabilities Induced by a Multivalued Mapping[J]. The Annals of Mathematical Statistics, 1967, 38(2):325-339.
doi: 10.1214/aoms/1177698950
[18]
Shafer G. A Mathematical Theory of Evidence[M]. Princeton University Press, 1976:17-24.
[19]
Dempster A P. A Generalization of Bayesian Inference[J]. Journal of the Royal Statistical Society: Series B (Methodological), 1968, 30(2):205-232.
doi: 10.1111/j.2517-6161.1968.tb00722.x
[20]
Fu K S. Pattern Recognition and Machine Learning[M]. Boston, MA: Springer US, 1971.
[21]
Devlin J, Chang M W, Lee K, et al. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding[C]// Proceedings of NAACL-HLT 2019. 2019:4171-4186.
[22]
Frigyik B A, Kapila A, Gupta M R. Introduction to the Dirichlet Distribution and Related Processes[R]. UWEE Technical Report, UQEETR-2010-0006.
( Song Kuiyong, Wang Nianbin, Wang Hongbin. Multivariate D-S Evidence Weighted Ensemble Classification Based on Shapelets[J]. Journal of Jilin University (Information Science Edition), 2021, 39(2):205-214.)
( Dong Zengshou, Deng Lijun, Zeng Jianchao. A New Improved D-S Algorithm Based on Weight of Evidence[J]. Computer Technology and Development, 2013, 23(5):58-62.)
[25]
Han Z B, Zhang C Q, Fu H Z, et al. Trusted Multi-View Classification[C]// Proceedings of the 9th International Conference on Learning Representations. 2021.
[26]
张睿. 基于SVM的中文文本分类相关算法研究与实现[D]. 昆明: 昆明理工大学, 2013.
[26]
( Zhang Rui. Research and Implementation of Chinese Text Classification Algorithm Based on SVM[D]. Kunming: Kunming University of Science and Technology, 2013.)
[27]
陈杨楠. 基于改进SVM算法的投诉文本分类研究[D]. 合肥: 合肥工业大学, 2019.
[27]
( Chen Yangnan. Research on Classification of Complaint Texts Based on Improved SVM[D]. Hefei: Hefei University of Technology, 2019.)
( Dang Jingyuan. Research and Design of Online Public Opinion Text Orientation Analysis System Based on Deep Learning[D]. Xi’an: Xidian University, 2019.)