期刊文献+

微信舆情主动防御系统及监测算法 被引量:2

Research on Active Defense System and Monitoring Algorithm of WeChat Public Opinion
原文传递
导出
摘要 【目的/意义】随着以微信为代表的社交软件的普及和社交网络的搭建,大众的舆论影响力不断提升,一旦舆论导向被动机不良的犯罪分子掌握,将会产生巨大的破坏力。【方法/过程】在此背景下,本文以蜜罐网络主动防御模型为基础,借助适应性聚类分析技术,对微信中的舆论信息进行实例结果分析。【结果/结论】验证了适应性聚类分析算法的效力和准确度,证明了投放诱饵数量与舆论调和间的正比关系,印证了本文所构建的蜜罐主动防御系统对社交媒体的舆情监控具有积极的作用。 [Puq)ose/signifieance] With the rapid development of SNS represented by WeChat, the public opinion's power is promoting. Once the public opinion is misused by the criminals, the outcome may be terrible. [ Method^process]This pa- per adopts the honeypot network of active defense model based on integration of text extraction and adaptive clustering tech- niques to extract WeCbat information. [Results/conclusion]The study shows that the elustering analysis algorithm has the obvious advantage in aceuraey and efficiency. The bait number and the public opinion control have direct proportion rela- tionship. The constructed honeypot in the paper has positive influences on the control of public opinion.
作者 徐萌 王晓 XU Meng WANG Xiao(Libaray of Hebei University of Science and Technology, ShOiazhuang 050000, Chin)
出处 《情报科学》 CSSCI 北大核心 2017年第8期40-46,共7页 Information Science
关键词 微信 舆情 蜜罐 主动防御 诱饵 WeChat public opinion honey pot active defense Bail
  • 相关文献

参考文献13

二级参考文献140

  • 1陈浩,何婷婷,姬东鸿.基于k-means聚类的无导词义消歧[J].中文信息学报,2005,19(4):10-16. 被引量:16
  • 2潘灶烽,汪小帆,李翔.可变聚类系数无标度网络上的谣言传播仿真研究[J].系统仿真学报,2006,18(8):2346-2348. 被引量:86
  • 3刘常昱,胡晓峰,司光亚,罗批.基于小世界网络的舆论传播模型研究[J].系统仿真学报,2006,18(12):3608-3610. 被引量:80
  • 4黄昌宁 等.对自动分词的反思[A]..语言计算与基于内容的文本处理[C].北京:清华大学出版社,2003,7.26-38.
  • 5[1]McCallum A, Nigam K. A Comparison of Event Models for Naive Bayes Text Classification. AAAI-98 Workshop on Learning for Text Categorization, 1998
  • 6[2]Meretakis D, Fragoudis Dimitris, Lu Hongjun, Likothanassis Spiros, Scalable Association-Based Text Classification. Proceedings of the 9th ACM Int Conf Information and Knowledge Management (CIKM'00), Washington, US, 2000, 5~11
  • 7[3]Antonie M, Osmar R. Text Document Categorization by Feature Association. Proceedings of the IEEE International Conference on Data Mining (ICDM'2002), 2002, 3: 19~26
  • 8[4]Deshpande Mukund, Karypis George. Using Conjunction of Attribute Values for Classification. Proceedings of the 11th ACM Int Conf Information and Knowledge Management (CIKM'02), 2002, 356~364
  • 9[5]Lesh Neal, Mohammed J, Zaki Ogihara Mitsunori. Mining Features for Sequence Classification. Proceedings of 5th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 1999, 342~346
  • 10[6]Mladenic D, Grobelnik M. Word Sequences as Features in Text-Learning. Proceedings of the 17th Electrotechnical and Computer Science Conference, Ljubljana, Slovenia: 1998, 145~148

共引文献437

同被引文献20

引证文献2

二级引证文献10

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部