Semantic relationship of contents using tensor factorization for self-growth social broadcasting

Abstract

The ability to predict the activities of users in Growth Social Broadcasting (GSB) is an important one for recommendation systems. The user activities can be represented in item of relationships involving three or more things. Such relationships can be represented as a tensor, and tensor factorization is becoming an increasingly important means for predicting users' possible activities. In this paper, we propose Self-Growth Social Broadcasting (SGSB) recommendation algorithm which help users find the articles that are interesting to read. The Self-Growth Social Broadcasting is representing the unstructured text data in the form of key concepts, synonyms and syn-sets which are all stored in the domain. The recommendation algorithm build the mind-map based on users behaviors to detect the genuine interests and predict current interest automatically and in real time by applying the thinking of relevance feedback. © 2016 IEEE.