In this paper we show how simple text mining and semantic network analysis may be used to (i) improve our theoretical understanding of idea generation, (ii) help people improve the creativity of their ideas. From a theoretical perspective, we contribute to the cognitive idea generation literature by establishing a link between the set of concepts used to form an idea and the creativity of the idea. Each idea contains a subset of the semantic network of concepts related to the topic. We show a prototypicality effect, such that the judged creativity of an idea may be predicted by the prototypicality of the semantic subnetwork associated with the idea. We show the robustness of this effect across 8 studies. From a practical perspective, we develop and test an online idea generation tool that helps users improve their ideas by suggesting words that would improve the prototypicality of their ideas' semantic subnetworks.