Computer Engineering and Applications ›› 2023, Vol. 59 ›› Issue (23): 263-272.DOI: 10.3778/j.issn.1002-8331.2306-0229

• Network, Communication and Security • Previous Articles     Next Articles

Research on Tracing Major Public Opinion Events Based on Double-Layer Blockchain

LIU Xin, WANG Haiwen, SUN Zhijian, YANG Dawei, PANG Mingjiang   

  1. 1.College of Computer Science and Technology, China University of Petroleum(East China), Qingdao,Shandong  266580, China
    2.Qingdao Confidential Technology Service Center, Qingdao,Shandong 266071, China
  • Online:2023-12-01 Published:2023-12-01

重大舆情事件的双层区块链溯源方法研究

刘昕,王海文,孙志坚,杨大伟,庞铭江   

  1. 1.中国石油大学(华东) 计算机与科学技术学院,山东 青岛 266580
    2.青岛市保密技术服务中心,山东 青岛 266071

Abstract: The future metaverse is a fully developed and personalized world based on trusted social networks. However, the information in social networks is multi-source and easy to be tampered with, making major public opinion events difficult to trace. To solve the above problems, a double-layer blockchain is constructed to realize the traceability of public opinion events. Firstly, Sentence-BERT model is used to extract sentence vectors of comments and the interest similarity among users is evaluated. Leiden algorithm is used for discovering the interest community. The comments chain is constructed with the users of interest communities as the nodes to store the tracking information, and using the community leaders as nodes to construct an interest community chain for storing the key words of the highest influence users. Then, a multi-source traceability evidence chain is formed based on the comments along with tracking information stored on the blockchain. Finally, the experimental results and the security analysis show that the average query delay of the blockchain is 110 ms and throughput is greater than 550 TPS, the proposed method is feasible in the trusted management of public opinion data and the traceability of major public opinion events.

Key words: public opinion tracing, blockchain, metaverse, social networks, community detection

摘要: 未来元宇宙是以可信社交网络为基础、个性化充分发展的世界,但目前社交网络中信息来源鱼龙混杂且易篡改,致使重大舆情事件难以溯源。针对以上问题,构建了舆情信息双层区块链实现舆情事件溯源。基于Sentence-BERT模型提取各用户的言论句向量并评估用户间兴趣相似度,利用Leiden算法实现兴趣社区发现,以兴趣社区用户为节点构建舆情信息链存储用户言论及其来源信息,以各兴趣社区领导者为节点构建兴趣社区链,存储高影响力用户言论关键词信息。以言论关键词检索兴趣社区链中潜在舆情源头社区,在舆情信息链中检索相关社区区块,多源信息以时间为序列形成多源头溯源证据链。实验结果显示双层区块链的平均查询延迟为110 ms,吞吐量大于550 TPS,结合安全性分析表明该方法在舆情数据可信管理、重大舆情事件可追溯方面有效可行。

关键词: 舆情溯源, 区块链, 元宇宙, 社交网络, 社区发现