Personalized Mention Probabilistic Ranking - Recommendation on Mention Behavior of Heterogeneous Social Network

Selecting a suitable person to mention on the Micro-blogging network, expressed as "@username", is a new aspect of recommendation system which carries great importance to promote user experience and information propagation. We comprehend information propagation as the reach, vitality, and effectiveness of tweet messages. In this case, we consider this mention recommendation as a probabilistic problem and propose our method named Personalized Mention Probabilistic Ranking to find out who has the maximal capability and possibility to help tweet diffusion by utilizing probabilistic factor graph model in the heterogeneous social network. A wide range of features are extracted and highlighted in our model, such as tag similarity, text similarity, social influence, interaction history and named entities. Experimental results show that our approach outperforms the state-of-art algorithms.