The pattern-based sequence classification system (PBSC) identifies regularly occurring patterns in sequential data and uses these patterns to predict meta-information. To illustrate the wide applicability of this approach, we classify speech-accompanying gestures produced by adults in order to predict their level of empathy. Previous research that focused on isolated gestures has shown that the frequency with which individuals produce certain speech-accompanying gestures is related to empathy. The current research extends these analyses by investigating the relationship between multi-gesture sequences and empathy. Patterns found in multi-gesture sequences prove to be more useful for predicting empathy levels in adults than patterns found in single gestures. This paper thus demonstrates that sequences of gestures contain additional information compared to gestures in isolation. More importantly, this study introduces PBSC as an effective method to incorporate time as an extra dimension in gestural communication, which can be extended to a wide range of sequential modalities.