Invited Speaker at OBSSR Methodology Seminar

Abstract

The age of Big Data has ushered in a wave of high-volume digital information and much of it is text based. Text mining is a form of data mining that involves collecting and analyzing large volumes of textual data to reveal patterns and relationships. Techniques for mining can be used to extract key concepts, spot trends, summarize content from documents and gain semantic understanding, and index and search text for use in predictive analytics. Text mining has become an important research process with many different commercial and academic applications, and it is becoming more widely applied in social science studies. This one-day methodology seminar sponsored by NIH OBSSR will present a basic introductory overview of principles and techniques of text mining for behavioral and social research and showcase some innovative health research examples. Attendees of this seminar will gain a broad understanding and appreciation for some of the different tools available to collect and analyze large volumes of text data, and they will learn about some notable example applications in behavioral and social sciences health research.