I propose a novel Ising-like model of language evolution. In a simple way, Ising-like models represent the countervailing tendencies towards convergence and change present in language evolution. In the ordinary Ising-model, a node on a graph, in this case representing a language speaker, interacts with all its neighbors. In contrast, in the model proposed here, a node only interacts with the neighboring node whose state-vector is most similar to its own. This reflects the tendency of people to interact with others who speak a similar language. Unlike the ordinary Ising model, which tends towards language continua, this new model allows language boundaries.