Most of methods proposed to overcome current issues in social networks are based on graph modeling. Finding influential users in social networks is no exception. An important disadvantage these methods are involved with is not considering non-structural attributes of network like user favorites and their content-based activities. The approach we are about to introduce can cover user's non-structural attributes. We will show that finding local influential users needs new methods to be done more efficiently. It will also be shown that procedures that are used for detecting outliers could be efficiently used for detecting influential users. The procedure that we would be providing is intended to use one of the prominent methods for finding outliers and results show that our method is more accurate compared to other methods of influential user’s detection.
Volume 11 | 01-Special Issue
Pages: 470-477