Microblog Label Recommendation Based on Matrix Decomposition Model

Recent years, with the development and popularization of mobile devices and network technologies, Microblog has become a socialized media, users not only participate in self-expression, interpersonal relationships, but also access to a variety of news and hot events. Label is to help the system understand the user, thereby pushing content and friends to the user may be interested in. This paper proposes to get information such as mutual attention, one-way attention, existing labels and so on from user data, use the matrix decomposition model to recommend the label to the user after analysis.