Using metaphor-annotated material that is sufficiently representative of the topical composition of a similar-length document in a large background corpus, we show that words expressing a discourse-wide topic of discussion are less likely to be metaphorical than other words in a document. Our results suggest that to harvest metaphors more effectively, one is advised to consider words that do not represent a discourse topic. Traditionally, metaphor detectors use the observation that a metaphorically used item creates a local incongruity because there is a violation of a selectional restriction, such as providing a non-vehicle object to the verb derail in Protesters derailed the conference. Current state of art in metaphor detection therefore tends to be “localistic ” – the distributional profile of the target word in its immediate grammatical or collocational context in a background corpus or a database like WordNet is used to determine metaphoricity