Research on False Public Opinion Detection in Social Network

Abstract

Abstract: The spread of false public opinion has hardly affected the orderly and healthy development of cyberspace, and the widespread use of social networks has exacerbated the malicious injection and spread of false public opinion. False public opinion is a social science concept that lacks specific extension in the research field of natural science. This paper specified the manifestation of false public opinion and expanded misleading information, false news, rumors, sarcasm, bullying, and malicious language into the extension of false public opinion to facilitate the analysis of the injection and dissemination of false public opinion from the perspective of natural science. The concept of the public opinion transmission cycle was integrated into false public opinion detection to more clearly and effectively depict early detection. The differences and emphasis of false public opinion detection research at various stages were analyzed. This paper summarized the outstanding research on false public opinion detection in recent years using a systematic literature review method, introduced feature engineering, technical route, available data sets, and evaluation indicators, and discussed the research and challenges faced by false public opinion detection technology.

Key words: social network, False public opinion detection, Extension manifestation;Early detection, Public opinion dissemination cycle

摘要： 虚假舆情的传播极大地影响了网络空间的有序健康发展，而社交网络的广泛使用在很大程度上加剧了虚假舆情的恶意注入与传播.虚假舆情是一个社会科学概念，在自然科学的研究领域缺少具体的外延.具体化了虚假舆情的表现形式，将误导信息、假新闻、谣言、讽刺、欺凌、恶意言论等拓展为虚假舆情的外延表现，以便从自然科学角度分析虚假舆情的注入与传播.同时，为了更清晰有效地刻画早期检测的概念，将舆情传播周期的概念融入虚假舆情检测，分析了在各个阶段进行虚假舆情检测研究的区别和侧重点.系统地总结了近年来在虚假舆情检测方面的突出研究，主要介绍了特征工程、技术路线、可用数据集以及评价指标等，并讨论了虚假舆情检测技术面临的研究与挑战.

关键词: 社交网络, 虚假舆情检测, 外延表现, 早期检测, 舆情传播周期

CLC Number:

TP391

王标, 卫红权, 王凯, 刘树新, 李燃, . 社交网络虚假舆情检测研究进展[J]. 信息安全研究, 2023, 9(11): 1034-.

References

［1］刘海明. 网络虚假舆情成因剖析［J］. 社会治理, 2018 (3): 6468［2］陈艳红, 杜艺薇. 虚假网络舆情的成因、影响及控制［J］. 电子政务, 2016 (5): 6875［3］Tandoc J R E C, Lim Z W, Ling R. Defining “fake news”: A typology of scholarly definitions［J］. Digital journalism, 2018, 6(2): 137153［4］Hussain N, Turab M H, Rasool G, et al. Spam review detection techniques: A systematic literature review［J］. Applied Sciences, 2019, 9(5): 987［5］陈燕方, 李志宇, 梁循, 等. 在线社会网络谣言检测综述［J］. 计算机学报, 2018, 41(7): 16481677［6］Della V M L, Tacchini E, Moret S, et al. Automatic online fake news detection combining content and social signals［C］ Proc of the 22nd Conf of Open Innovations Association (FRUCT). Piscataway, NJ: IEEE, 2018: 272279［7］Ghanem B, Rosso P, Rangel F. An emotional analysis of false information in social media and news articles［J］. ACM Trans on Internet Technology, 2020, 20(2): 118.［8］Felbo B, Mislove A, Sogaard A, et al. Using millions of emoji occurrences to learn anydomain representations for detecting sentiment, emotion and sarcasm［J］. arXiv preprint, arXiv: 170800524, 2017［9］Dani H, Li J, Liu H. Sentiment informed cyberbullying detection in social media［C］ Proc of the Joint European Conf on Machine Learning and Knowledge Discovery in Databases. Berlin: Springer, 2017: 5267［10］Ruchansky N, Seo S, Liu Y. Csi: A hybrid deep model for fake news detection［C］ Proc of the 2017 ACM on Conf on Information and Knowledge Management. New York: ACM, 2017: 797806［11］Ma T, Zhou H, Tian Y, et al. A novel rumor detection algorithm based on entity recognition, sentence reconfiguration, and ordinary differential equation network［J］. Neurocomputing, 2021, 447: 224234［12］Monti F, Frasca F, Eynard D, et al. Fake news detection on social media using geometric deep learning［J］. arXiv preprint, arXiv: 190206673, 2019［13］Cao R, Lee R KW, Hoang TA. Deephate: Hate speech detection via multifaceted text representations［C］ Proc of the 12th ACM Conf on Web Science. New York: ACM, 2020: 1120［14］Bouazizi M, Ohtsuki T O. A patternbased approach for sarcasm detection on twitter［J］. IEEE Access, 2016, 4: 54775488［15］Singh V K, Ghosh S, Jose C. Toward Multimodal Cyberbullying Detection［C］ Proc of the CHI Conf Extended Abstracts on Human Factors in Computing Systems. New York: ACM, 2017: 20902099［16］Zhou X, Jain A, Phoha V V, et al. Fake news early detection: A theorydriven model［J］. Digital Threats: Research and Practice, 2020, 1(2): 125［17］Bian T, Xiao X, Xu T, et al. Rumor detection on social media with bidirectional graph convolutional networks［C］ Proc of the AAAI Conf on Artificial Intelligence. Menlo Park, CA: AAAI, 2020: 549556［18］Kwon S, Cha M, Jung K. Rumor detection over varying time windows［J］. PloS One, 2017, 12(1): e0168344［19］Chen T, Li X, Yin H, et al. Call attention to rumors: Deep attention based recurrent neural networks for early rumor detection［C］ Proc of the PacificAsia Conf on Knowledge Discovery and Data Mining. Berlin: Springer, 2018: 4052［20］Ma J, Gao W, Wong KF. Rumor detection on twitter with treestructured recursive neural networks［G］ Association for Computational Linguistics. Stroudsburg, PA: ACL, 2018［21］杨小芳, 李子航, 贺武华. 从新冠疫情的微博热搜看网络舆情演变及治理［J］. 西南交通大学学报: 社会科学版, 2021, 22(4): 3440［22］Vicario M D, Quattrociocchi W, Scala A, et al. Polarization and fake news: Early warning of potential misinformation targets［J］. ACM Trans on the Web, 2019, 13(2): 122［23］Pierri F, Piccardi C, Ceri S. Topology comparison of Twitter diffusion networks effectively reveals misleading information［J］. Scientific Reports, 2020, 10(1): 19［24］Ferrara E, Varol O, Davis C, et al. The rise of social bots［J］. Communications of the ACM, 2016, 59(7): 96104［25］Shu K, Bernard H R, Liu H. Studying fake news via network analysis: Detection and mitigation［G］. Emerging Research Challenges and Opportunities in Computational Social Network Analysis and Mining. Berlin: Springer, 2019: 4365［26］Shu K, Wang S, Liu H. Beyond news contents: The role of social context for fake news detection［C］ Proc of the 12th ACM Int Conf on Web Search and Data Mining. New York: ACM, 2019: 312320［27］Zhou X, Zafarani R. A survey of fake news: Fundamental theories, detection methods, and opportunities［J］. ACM Computing Surveys, 2020, 53(5): 140［28］Ye A, Wang L, Wang R, et al. An endtoend rumor detection model based on feature aggregation［J］. Complexity, 2021, 2021: 116［29］Wu L, Li J, Hu X, et al. Gleaning wisdom from the past: Early detection of emerging rumors in social media［C］ Proc of the SIAM Int Conf on Data Mining. Philadelphia, PA: SIAM, 2017: 99107［30］Vosoughi S, Roy D, Aral S. The spread of true and false news online［J］. Science, 2018, 359(6380): 11461151［31］Manzoor S I, Singla J. Fake news detection using machine learning approaches: A systematic review［C］ Proc of the 3rd Int Conf on Trends in Electronics and Informatics (ICOEI). Piscataway, NJ: IEEE, 2019: 230234［32］Zhao Z, Resnick P, Mei Q. Enquiring minds: Early detection of rumors in social media from enquiry posts［C］ Proc of the 24th Int Conf on World Wide Web. New York: ACM, 2015: 13951405［33］Kwon S, Cha M, Jung K, et al. Prominent features of rumor propagation in online social media［C］ Proc of the 13th IEEE Int Conf on Data Mining. Piscataway, NJ: IEEE, 2013: 11031108［34］Castillo C, Mendoza M, Poblete B. Information credibility on twitter［C］ Proc of the 20th Int Conf on World Wide Web. New York: ACM, 2011: 675684［35］Balakrishnan V, Khan S, Arabnia H R. Improving cyberbullying detection using Twitter users’ psychological features and machine learning［J］. Computers & Security, 2020, 90: 101710［36］Yang Z, Wang C, Zhang F, et al. Emerging rumor identification for social media with hot topic detection［C］ Proc of the 12th Web Information System and Application Conf (WISA). Piscataway, NJ: IEEE, 2015: 5358［37］Aldwairi M, Alwahedi A. Detecting fake news in social media networks［J］. Procedia Computer Science, 2018, 141: 215222［38］Yang S, Shu K, Wang S, et al. Unsupervised fake news detection on social media: A generative approach［C］ Proc of the AAAI Conf on Artificial Intelligence. Menlo Park, CA: AAAI, 2019: 56445651［39］Takahashi T, Igata N. Rumor detection on Twitter［C］ Proc of the the 6th Int Conf on Soft Computing and Intelligent Systems, and the 13th Int Symp on Advanced Intelligence Systems. Piscataway, NJ: IEEE, 2012: 452457［40］Chen Y, Sui J, Hu L, et al. Attentionresidual network with CNN for rumor detection［C］ Proc of the 28th ACM Int Conf on Information and Knowledge Management. New York: ACM, 2019: 11211130［41］Lv S, Zhang H, He H, et al. Microblog rumor detection based on comment sentiment and CNNLSTM［M］ Artificial Intelligence in China. Berlin: Springer, 2020: 148156［42］Kaliyar R K, Goswami A, Narang P, et al. FNDNet—A deep convolutional neural network for fake news detection［J］. Cognitive Systems Research, 2020, 61: 3244［43］Agarwal A, Mittal M, Pathak A, et al. Fake news detection using a blend of neural networks: An application of deep learning［J］. SN Computer Science, 2020, 1(3): 19［44］Almakhadmeh Z, Tolba A. Automatic hate speech detection using killer natural language processing optimizing ensemble deep learning approach［J］. Computing, 2020, 102(2): 501522［45］Jain D, Kumar A, Garg G. Sarcasm detection in mashup language using softattention based bidirectional LSTM and featurerich CNN［J］. Applied Soft Computing, 2020, 91: 106198［46］Miao X, Rao D, Jiang Z. Syntax and sentiment enhanced BERT for earliest rumor detection［C］ Proc of the CCF Int Conf on Natural Language Processing and Chinese Computing. Berlin: Springer, 2021: 570582［47］Mozafari M, Farahbakhsh R, Crespi N. A BERTbased transfer learning approach for hate speech detection in online social media［C］ Proc of the Int Conf on Complex Networks and Their Applications. Berlin: Springer, 2019: 928940［48］Paul S, Saha S. CyberBERT: BERT for cyberbullying identification［J］. Multimedia Systems, 2022, 28(6): 18971904［49］Singh J P, Kumar A, Rana N P, et al. Attentionbased LSTM network for rumor veracity estimation of tweets［J］. Information Systems Frontiers, 2022, 24(2): 459474［50］Bisht A, Singh A, Bhadauria H, et al. Detection of hate speech and offensive language in Twitter data using lstm model［G］. Recent Trends in Image and Signal Processing in Computer Vision. Berlin: Springer, 2020: 243264［51］Kumar A, Narapareddy V T, Srikanth V A, et al. Sarcasm detection using multihead attention based bidirectional LSTM［J］. IEEE Access, 2020, 8: 63886397［52］Wang Z, Guo Y, Wang J, et al. Rumor events detection from chinese microblogs via sentiments enhancement［J］. IEEE Access, 2019, 7: 103000103018［53］Li L, Cai G, Chen N. A rumor events detection method based on deep bidirectional GRU neural network［C］ Proc of the 3rd IEEE Int Conf on Image, Vision and Computing (ICIVC). Piscataway, NJ: IEEE, 2018: 755759［54］Lotfi S, Mirzarezaee M, Hosseinzadeh M, et al. Detection of rumor conversations in Twitter using graph convolutional networks［J］. Applied Intelligence, 2021, 51(7): 47744787［55］Xu D, Liu Q, Zhu L, et al. GCNRDM: A social network rumor detection method based on graph convolutional network in mobile computing［J］. Wireless Communications and Mobile Computing, 2021, 2021: 111［56］Song C, Shu K, Wu B. Temporally evolving graph neural network for fake news detection［J］. Information Processing & Management, 2021, 58(6): 102712［57］Medeiros F D C, Braga R B. Fake news detection in social media: A systematic review［C］ Proc of XVI Brazilian Symp on Information Systems. New York: ACM, 2020: 18［58］Santia G C, Williams J R. Buzzface: A news veracity dataset with facebook user commentary and egos［C］ Proc of the 12th Int AAAI Conf on Web and Social Media. Menlo Park, CA: AAAI, 2018: 531540［59］Tacchini E, Ballarin G, Della Vedova M L, et al. Some like it hoax: Automated fake news detection in social networks［J］. arXiv preprint, arXiv: 170407506, 2017［60］Ahmed H, Traore I, Saad S. Detecting opinion spams and fake news using text classification［JOL］. Security and Privacy, 2018, 1(1) ［20230209］. https:doi.org10.1002spy2.9［61］Wang W Y. “liar, liar pants on fire”: A new benchmark dataset for fake news detection［J］. arXiv preprint, arXiv: 170500648, 2017［62］Nrregaard J, Horne B D, Adal S. Nelagt2018: A large multilabelled news dataset for the study of misinformation in news articles［C］ Proc of the Int AAAI Conf on Web and Social Media. Menlo Park, CA: AAAI, 2019: 630638［63］Patwa P, Sharma S, Pykl S, et al. Fighting an infodemic: Covid19 fake news dataset［J］. arXiv preprint, arXiv: 201103327, 2020［64］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): 171188［65］Ma J, Gao W, Mitra P, et al. Detecting rumors from microblogs with recurrent neural networks［C］ Proc of the 25th Int Joint Conf on Artifificial Intelligence (IJCAI 2016). San Francisco, CA: Morgan Kaufmann, 2016: 38183824［66］Zubiaga A, Liakata M, Procter R, et al. Analysing how people orient to and spread rumours in social media by looking at conversational threads［J］. PloS One, 2016, 11(3): e0150989［67］Derczynski L, Bontcheva K, Liakata M, et al. SemEval2017 Task 8: RumourEval: Determining rumour veracity and support for rumours［J］. arXiv preprint, arXiv: 170405972, 2017［68］Ferreira W, Vlachos A. Emergent: A novel dataset for stance classification［C］ Proc of the Conf of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, PA: ACL, 2016

[1]	. Application Study on Weibo Network Public Opinion Communication Based on Social Network Analysis [J]. Journal of Information Security Reserach, 2023, 9(7): 693-.
[2]	. Social Network Rumor Suppression Scheme Based on Opinion Leaders [J]. Journal of Information Security Reserach, 2023, 9(1): 57-.
[3]	. [J]. Journal of Information Security Reserach, 2022, 8(8): 825-.
[4]	. [J]. Journal of Information Security Reserach, 2022, 8(7): 718-.
[5]	. [J]. Journal of Information Security Reserach, 2022, 8(6): 622-.
[6]	. "Believe in authority or not"? A Study on Social Media and Public Opinion Response in COVID-19 Pandemic [J]. Journal of Information Security Research, 2021, 7(2): 155-165.
[7]	. A Spammer Detection Method Based on Social Network Structure [J]. Journal of Information Security Research, 2019, 5(11): 993-999.
[8]	. A Method of Uncertain Graphs Based on Node Characteristics for Preserving Privacy in Social Networks [J]. Journal of Information Security Research, 2018, 4(6): 533-538.
[9]	. A Method Based on Wave Filtering to Evaluate the Intensity of Privacy Preserving on Social Network [J]. Journal of Information Security Research, 2018, 4(4): 315-321.
[10]	Li Yang. The Research of Governance Path of Social Network Based on the Key Node [J]. Journal of Information Security Research, 2016, 2(12): 1110-1113.
[11]	Li Yang Lv Xin. Security Problems and Coping Strategies of Cyberspace in Social Network [J]. Journal of Information Security Research, 2015, 1(2): 126-130.