GameSage is a companion tool to GameNet that allows a user to insert a new game concept into the natural language processing model. The user’s input text is coverted into a LSA vector and folded-in to the pre-computed model. The result page is a standard GameNet entry for the user’s speculative game, and allows designers looking to verify an idea’s originality, or compare it with similar titles, a quick way to explore the space of related examples. This is a collaboration with James Ryan at the Expressive Intelligence Studio.

GameSage is live at this link. For more information on the model and GameSage please check out publications.