The Power of the Stories Hidden in the Data

Kristian Hammond (Northwestern Computer Science)
Location: Online Level:

In business, there is a growing awareness that decisions should be evidence based. That is, based on the analysis of the facts and figure that flow from monitoring business practice. While tremendous issues remain, it is clear that businesses are driving towards a model of decision making based on evidence.

In other realms, this idea has had a harder time taking hold. In government, public policy, and education, this notion of evidence based decision making has had a harder time making inroads. In part, this is because many of the issues involved in these decisions have both ideological and emotional elements to them. But these issues aside, there is still the problem of understanding and communicating the data. In fact I would argue that the lack of appropriate analysis, insight and communication adds to the amplies the ideological and emotional issues simply because the data and te insight contained in it cannot be communicated to bread audiences.

One way to solve this problem is to build systems that not only analyze the data but also transform it into stories and insight. That is, transform it into the natural vehicle for communication that we use everyday. The question is, how do we do this in a way that allows us to use the data to tell both the broader stories contained within as well as the singular stories to the “audience of one” that is needed to create relevant communication

In this talk, I will outline a core technology that does exactly this. Given a data set and the possible stories contained in it, this automatically generates stories that communicate the insights (trends, correlations, comparisons) that is all too often hidden within it. I will describe the technology and discuss examples from education, pharmacology and medical informatics that demonstrate how pulling the story from data can be used to drive communication and understanding in areas that desperately need it.

Photo of Kristian Hammond

Kristian Hammond

Northwestern Computer Science

Kristian Hammond is Narrative Science’s chief scientist and a professor of computer science and journalism at Northwestern University. His research has been primarily focused on artificial intelligence, machine-generated content, and context-driven information systems. He currently sits on a United Nations policy committee run by the United Nations Institute for Disarmament Research (UNIDIR). Kris was also named 2014 innovator of the year by the Best in Biz Awards. He holds a PhD from Yale.