Videos

Understanding History through Topic Modeling

Presenter
May 25, 2016
Abstract
David Blei Columbia University Significant events are characterized by interactions between entities (e.g., countries, organizations, individuals) that deviate from typical interaction patterns. Investigators, such as historians, commonly read large quantities of text to construct an accurate picture of who, what, when, and where and event happened. In this work, we present the Capsule model for analyzing documents. Capsule identifies and characterizes events of potential significance. Specifically, we develop a model based on topic modeling to distinguish between topics that describe ``business-as-usual'' and topics that deviate from these patterns. To demonstrate this model, we analyze real-world datasets, including a corpus of over 2 million US State Department cables from the 1970s.