As the number of social networking services (SNS) and their users grow, so does the complex-ity of individual networks as well as the amount of information to be consumed by the users. It is inevitable to reduce the complexity and infor-mation overload, and we have embarked explor-ing topical aspects of SNS to form refined topic-based semantic social networks. Our current work focuses on conversational aspects of SNS and attempt to utilize the notions of topic diversi-ty and topic purity between two users sharing conversations. This topic-based analysis of SNS makes it possible to show different types of users and their conversational characteristics. It also shows the possibility of breaking down a huge “syntactic” social network into topic-based ones based on different interaction types, so that the resulting semantic social networks can be useful in designing various targeted services on online social networks.