Finding Key Users Of Microblogs Based On Users' Attribute

With the rapid development of Web 2.0 technology and the continuous improvement of information transmission speed,the research on the key users that promote the dissemination of information becomes a very hot topic.Therefore,the key user mining technology to promote information transmission has positive practical significance for network security,public opinion supervision and network marketing.On the network platform of Microblog,because users play an important role in the process of information communication,its characteristic attribute is significant to the efficient mining of key users.The user characteristic attribute is represented as a time attribute and an interactive attribute.The time attribute is reflected in the time of Microblog users'tweeting;The interactive behavior attribute is reflected in the user's behavior on the social platform,including forwarding,comment and so on.Considering the timeliness of the microblogging topic and the feature of interaction between the users,therefore,this thesis put forward a key user's mining algorithm based on user interaction to effectively find topic-sensitive key users.Firstly,the selection and acquisition of microblog data source are introduced.Secondly,this thesis starting from the time and the interaction attribute of the user,introduces the definition of key users in microblogging topic and its relevant characteristics.In that the traditional models ignored the influence of user interaction and time attribute,the model fused the time property and the characteristics of interaction between the user together in the model at the first time,and the MUR algorithm was put forward with the combination of the microblogging network structure.Finally,this thesis compared the algorithm with the classical PageRank algorithm and TS algorithm.The experimental results show that the model is more reasonable in terms of timeliness and topic driving,certificating the rationality and validity of the model.