Viral Marketing in an Online Discussion Forum

Abstract

Online opinion leaders play an important role in the dissemination of information in discussion forums. They are a high-priority target group for viral marketing campaigns. On an average, an opinion leader will tell about his or her experience with a product or company to 14 other people. It is important to identify such opinion leaders from data derived from online activity of users. We present an approach to modeling an online discussion forum using a two-mode social network called an affiliation network. Studying structural properties of the social network is a useful first step. In order to gain insight into other attributes of online users, it is necessary to follow a data mining approach. These observations lead to the representation of the online profile of each user as a set of attributes based on the online behavior of a user and that of other users as well. We present an approach to identification of opinion leaders using the K-means clustering algorithm. This approach does not require prior knowledge of the user’s opinions or membership in other forums.