User Profile Research Based On Social Network

As the typical application in Web2.0 Era,social networking services(SNS)get a explosive growth and ubiquitous mobility is a sign.In fact,the development of SNS is transfering the information management from offline to online,making the large amount of content in virtual networks.These abundant social information can fully show a user's portrait.What is more,a person of digitization can be constructed through the large information.In the meantime,user portrait is the base of personalized recommendation,personalized search,etc which contain a huge commercial value.Based on the above background,this paper mainly study the problem of user portrait construction based on social networks.The scope of the user portrait is too big so that I select interest and occupation as our research point which is more important.This paper proposed tag-based user interest discovery algorithm through key words extraction and user occupation classifier algorithm based on social network.However the research of occupation is few so that this paper make some tentative research and this bring us a lot of challenges.The algorithms of this paper can ensure the accuracy of identifying user's interests and occupation in specific application scenarios and can meet the requirements of data mining on the basis of Chinese socail network.In order to give ordinary users a more vividly view of the results,a user portrait construction system called "UPS" has been developed.In addition,the user interest discovery algorithm has applied to the recommend areas and has been proved effective and reliable.