Construction of Structured Heterogeneous Networks from Massive Text Data: Extended Abstract

Abstract

Network data analytics is important, powerful, and exciting. How big role may network data analytics play in the real world? Much real-world data is unstructured, in the form of natural language text. A grand challenges on big data research is to develop effective and scalable methods to turn such massive text data into actionable knowledge. In order to turn such massive unstructured, text-rich, but interconnected data into knowledge, we propose a data-to-network-to-knowledge (D2N2K) paradigm, that is, first transform data into relatively structured heterogeneous information networks, and then mine such text-rich and structure-rich heterogeneous networks to generate useful knowledge. We argue that such a paradigm represents a promising direction and network data analytics will play an essential role in transforming data to knowledge. However, a critical bottleneck in this game is mining structures from text data. We present our recent progress on developing effective methods for mining structures from massive text data and constructing structured heterogeneous information networks.