We investigate the appropriateness of using a technique based on support vector machines for identifying thematic structure of text streams. The thematic segmentation task is modeled as a binary classification problem, where the different classes correspond to the presence or the absence of a thematic boundary. Experiments are conducted with this approach by using features based on word distributions through text. We provide empirical evidence that our approach is robust, by showing good performance on three different data sets. In particular, substantial improvement is obtained over previously published results of word distribution based systems when evaluation is done on a corpus of recorded and transcribed multi-party dialogs.