Chronic diseases like Heart Failure are widespread in the ageing population. Affected patients can be treated with the aid of a disease management program, including a telemedical collaborative network. Evaluation of a currently used system has shown that the information of the textual communication is of pivotal importance for the collaboration in the network. Thus, the challenge is to make this unstructured information useable, potentially leading to a better understanding of the collaboration so as to optimize the processes. This paper presents the setup of an analysis pipeline for processing textual information automatically, and, how this pipeline can be utilized to train a model that is able to automatically classify the written messages into a set of meaningful task and status categories.