While social network analysis often focuses on graph structure of social actors, an increasing number of communication networks now provide textual content within social activity (email, instant messaging, blogging, collaboration networks). We present an open source visualization software, GraphDuplex, which brings together social structure and textual content, adding a semantic dimension to social analysis. GraphDuplex eventually connects any number of social or semantic graphs together, and through dynamic queries enables user interaction and exploration across multiple graphs of different nature.