Research And Application Of Weibo User Influence On Social Network

With the coming of the information explosion,the Internet has entered the era of Web2.0.With the characteristics of timely information update,fast information dissemination and strong interactivity,Weibo has become the mainstream social media network platform.As high-impact users in the Weibo platform can play a role in guiding public opinion and promoting commodity marketing,it is especially important to excavate the users with high-impact.Aiming at solving the problems of the incomplete influence of Weibo users on the factors and interactions of Weibo users and the incorrect analysis of user network structure,which leads to the inaccurate calculation of the influence of Weibo users,this thesis proposes a micro-blog user influence based on user's self-factors and interaction computing model(MBUI-SFIM)and a Micro-blog user influence based on Information Entropy computing model(MBUI-IEM).The main research work is divided into the following three points:1 This thesis analyzes the two factors of Weibo users' self-factors and interaction behaviors,and proposes the MBUI-SFIM method to calculate the influence of ordinary Weibo users.The method considers the direct influence and indirect influence of Weibo users.In the user's direct influence calculation,the user's initial influence is calculated by analyzing the user's own factors,and then the user's interaction behavior is analyzed to calculate the communication ability.Finally,based on the PageRank algorithm,the direct influence of the user is calculated by combining the initial influence of user and the spread ability.In the calculation of the indirect influence,the indirect influence of the user is calculated according to the connection path of the non-adjacent user.The validity of the MBUI-SFIM method in the calculation of the influence of Weibo common users is verified by experiments.2 Based This thesis proposes the MBUI-IEM method based on information entropy to calculate the influence of Weibo authentication users.Firstly,the method establishes the connection graph based on the interaction behavior of Weibo users.On this basis,the information entropy is used to calculate the key elements affecting the Weibo users,then the direct influence of the users is obtained.Then,the user adjacency matrix is established according to the microblog user connection relationship.The indirect influence of the user is calculated by user adjacency matrix.Finally the total influence of the user is calculated based on the direct influence and the indirect influence.The validity of the MBUI-IEM method in the calculation of the influence of Weibo authentication users is verified by experiments.3 This thesis designs and implements a microblog retrieval system based on the influence of Weibo users.The MBUI-SFIM method is used in the ranking search of ordinary users,and the MBUI-IEM method is used in the ranking search of authenticated users.The system is more accurate in search information than other systems.