Data Science Day @ Columbia University

Please note that this demo will only be available until 3:45PM.

We explore the use of Big Data tools to shed new light on the idea generation process, automatically “read” ideas in order to identify promising ones, and help people be more creative. The literature suggests that creativity results from the optimal balance between novelty and familiarity, which should be measured based on the combinations of words in an idea. We build semantic networks where nodes represent word stems relevant to a particular idea generation topic, and edge weights capture the novelty vs. familiarity of word stem combinations (i.e., the weight of an edge that connects two word stems measures their scaled co-occurrence). Each idea contains a set of word stems, which form a semantic subnetwork. The edge weight distribution in that subnetwork reflects how the idea balances novelty with familiarity. Consistent with the “beauty in averageness” effect, we find that ideas with semantic subnetworks that have a more prototypical edge weight distribution are judged as more creative. Practically, we demonstrate how our research can be used to automatically identify promising ideas, and recommend words to users on the fly to help them improve their ideas.