Rumor Identification Based On Sina Micro-blog Platform

With the rapid development of information technology,social media such as micro-blog and WeChat emerge as the times require.While social networking has brought convenience to people,it has also provided a breeding ground for the spread and spread of rumors.The spread of rumors can cause terrible consequences such as trust crisis and social panic.Sina micro-blog is an information sharing and communication platform for the public to provide entertainment and leisure life.At present,Sina micro-blog is the most active social network platform in China.The free and convenient information dissemination has become an important way of spreading rumors.This article selects Sina micro-blog to carry out the research of rumor recognition.Taking Sina micro-blog as a research object,identifying rumors in micro-blog instantly is of great significance for the harmonious development of society.In recent years,more and more attention has been paid to the credibility of social networks.Scholars at home and abroad have done a lot of research on the credibility of social networks.The main idea of the mainstream research is to use machine learning method to build classifiers combining user,text and propagation features.Firstly,this paper analyzes the research status of the topic at home and abroad,analyzes the main research methods used to detect the social network rumor and its need to improve.Secondly,it analyzes the characteristics of sina micro-blog rumor and then uses the method of text mining to screen out the topic of the candidate rumor.Then we propose the use of e collective intelligence and machine learning methods to identify the purpose of the rumor.In the case of a given large range of topics,the rumor recognition ability of sina micro-blog users is classified according to the machine learning method and the user's own characteristics,and then as a feature of the identification of rumors,the experimental results show that After introducing the feature of user recognition capability level,the classifier's recognition accuracy is improved.