基于极大似然估计的谣言追溯方法及对策研究  

Research on Rumor Tracking Method and Countermeasures Based on Maximum Similarity Estimation

作　　者：吴尤可[1] 

机构地区：[1]华侨大学经济与金融学院,泉州362021

出　　处：《情报学报》2016年第1期48-54,共7页Journal of the China Society for Scientific and Technical Information

基　　金：福建省2015年度社科项目"危险性舆情控制的法规建设研究"(FJ2015B154)资助

摘　　要：谣言借助现代信息技术可以飞速地传播,可能给社会造成极大的负面影响。如何快速、准确地找到谣言散播的始作俑者具有重要意义。本文从社交网络技术这一新的视角对谣言源头追溯进行了研究,基于观测到的部分节点状态来追溯谣言的源头。在锁定一个小范围的疑似源头节点集后,利用极大似然估计法来对疑似源头节点进行检查,从而找到最终的谣言源头。通过实验验证,该方法相对于传统谣言追溯方法大大提高了准确性。基于对追溯技术的分析,进而探讨了追溯谣言的对策,为进行谣言源头追溯的政策性制定提供了理论依据及建议。Rumor can spread rapidly based on modern information technology, which may makes harmful influences upon society. How to find the sources of rumors in a rapid and accurate way is of great importance. This paper studies the rumor tracing technology from the perspective of social networks. An algorithm based on the states of a few of observed nodes is designed, which uses ＂ Maximum Similarity Estimation＂ method to find the sources of rumors after narrowing the scope of suspected nodes. Experiment results show that it outperforms traditional method largely. Furthermore, based on the analysis of tracing technology, we discuss the policies for controlling the spread of rumors and tracing them, which provides theoretical basis and suggestion for the government.

关 键 词：社交网络 谣言追溯 部分观测 政策建议 

分 类 号：G206[文化科学—传播学]