| In the context of the rapid development of Web 2.0,microblogging as a new social media has greatly changed the traditional social network form,has been widely disseminated.The form of social networking provided by microblogging facilitates the acquisition,sharing and exchange of information.In the mobile Internet technology and location-based services,people can be through microblogging and other social platforms anytime,anywhere access to information,sharing of information.In this process,a large amount of data containing geographic location information has been continuously produced.The microblogging data containing the geographical location information associates the virtual network space with the real geographical space,and the information contained in it is worth digging.This paper takes the microblogging data of Xi’an as the main research object,studies the temporal and spatial distribution characteristics of microblogging data and the extraction of microblogging text information.The main research work of this paper is as follows:1.Analyze the temporal and spatial distribution of microblogging data.Based on the location information in microblogging data,the distribution characteristics of time dimension,spatial dimension and space-time dimension are studied respectively.The data visualization technique is used to present the distribution feature,and the difference and trend of distribution are analyzed briefly.2.Use the clustering algorithm to extract hotspots in the city.Aiming at the location information in microblogging data,the clustering analysis is carried out to extract hotspots in the city,which is a further study on the spatial distribution of microblogging data.The experimental results show that,to a certain extent,the spatial location information of the microblogging data can be extracted into the hotspots in the city according to the spatial aggregation of the location data.3.Use text processing technology to extract microblogging keywords.In order to extract the content keywords from the time dimension and the spatial dimension,the text information of the simplified summary is obtained by using the text processing technology in the complicated text content of the microblogging data. |
