Most online social networking services provide a feature for users to build groups. The web service has both user profiles describing user interests and behavior data such as browsing contents. It can assist users to join groups by recommending relevant groups. In this paper, we have proposed a novel method to connect users across multiple services based on user-labeled tags. Tags represent interests of a user and have advantages in terms of the privacy, up-to-dateness, and service coverage. We have collected tags from six popular web services. We have analyzed tag usage patterns and observed that the popularity of tags is highly skewed and dependent on the web services. We have also found that frequently used tags of a single user change over time. Through user study, we show that the vector space model combined with intra-personomy normalization is the promising to find other users with similar interests.