Text Mining: Digging Deep for Knowledge

Introduction

Text Mining and the Research Library: The Humanities and Beyond

In his presentation Bernard Reilly will:

• Survey text mining practice in various fields of research, including the humanities, public policy, economics, and linguistics
• Briefly discuss the relationship between text mining, data visualization, and artificial intelligence
• Examine the issues that arise for libraries in securing the ability and right to text mine from commercial database publishers.  

Enriching the Social Sciences Through Text Mining

Text mining and semantic technologies are commonplace in scientific, technical and medical circles. Text mining in the social sciences is more experimental, arguably more exciting, and becoming increasingly important to the organization and discovery of scholarship.

This is why increasing numbers of publishers are mining their own content to add structure, metadata and insight. This talk will look at how we mine our own content at SAGE to improve the researcher experience, covering questions such as:

• How do  you teach a computer to read social science content?
• What are the challenges presented by a highly context-sensitive area like the social sciences?
• How do you structure information that is meaningless without its original context?
• What's the role for human indexers in a world where computers are getting better at understanding meaning?

The HathiTrust Research Center: Enabling New Knowledge Through Shared Infrastructure

The HathiTrust Research Center (HTRC) enables computational access for nonprofit and educational users to published works in the public domain and, in the future, on limited terms to works in-copyright from the HathiTrust. The HathiTrust digital library, containing 14 million volumes spnanning various times and locations, along with HTRC's non-consumptive tools and services, provide scholars a unique opportunity of answering their research qeustions based upon this rich resource. One most prominent use of HathiTrust volumes is its support on text mining on this large-scale corpus. In this talk, we will briefly present an overview of HTRC, its tools, resources, and services.

*The HTRC is a collaborative research center launched jointly by Indiana University and the University of Illinois, along with the HathiTrust Digital Library, to help meet the technical challenges of dealing with massive amounts of digital text that researchers face by developing cutting-edge software tools and cyberinfrastructure to enable advanced computational access to the growing digital record of human knowledge.