Ranking the Influence Users in a Social Networking Site Using an Improved Topsis Method

With the wide spread popularity of social networking sites (SNS), enterprise organizations have started to explore the business opportunities in SNS such as Facebook to conduct targeted marketing and reputation management. Customers or users tend to trust the opinion of other customers or users, especially those with prior experience of a product or service, rather than company marketing. One of the important challenges to these enterprises is to conduct cost-effective marketing and reputation management on SNS through influencing users. When it comes to marketing, the users’ influence is associated with a certain topic or field on which people have different levels of preference and expertise is called homophily. In order to identify and predict influential users in a specific topic/subject more effectively, this paper introduces a new method to effectively identify the most influence users, who can generate the maximum of total benefit with respect to specific topics or business situations. This method uses homophily characteristics along with the technique for order preference by similarity to ideal solution (TOPSIS). Using this improved TOPSIS method, influencing users are identified and ranked on a Facebook dataset and compared against with TOPSIS method with no homophily. The experimental results show that how well the proposed technique precociously identify and rank influential users based on a certain topic or