In this paper, we describe a multi-modal approach to segmenting news video based on the perceived shift in content. We divide up a video document into logically coherent semantic units known as stories. We investigate a number of multimedia features, which serve as potential indicators of a change in story in order to determine which are the most effective. The efficacy of our approach is demonstrated by the performance of our prototype, where a number of feature combinations exceed the performance of other state of the art story segmenters by 18%.