In this article, we address the problem of confusion and co-text-loss in chat communication, identify requirements for a solution, discuss related work and present a new approach for addressing co-text loss in text-based chats. We report about first experiences with our solution and give an outlook on future work directions. The core idea of our solution MuViChat (multiple-visualization chat) is to support multiple visualizations of referenced chat transcripts in which users can choose their preferred view. The multiple visualizations offer different possibilities to follow and understand a communication and thereby diminish chat confusion which often occurs in standard chat systems. By enabling the recording and replaying of chat discussions and an extensible modular architecture we are supporting evaluation and further integration of advanced visualization concepts.