9728太阳集团学术论坛系列

SEIS Academic Forum Series (No. 737)

Forum on Intercultural Studies

Modern methods for text analysis

Speaker: Jeffrey R. Tharsen Ph.D.

Time: 15:00-17:00

Date: 8 October, 2019 (Tuesday)

Venue: Room 111, School of English and International Studies

Abstract:

In recent years there has been growing interest in the social sciences for computational methods that allow large-scale quantitative studies to be performed automatically. This has produced studies ranging from the analysis of massive social networks to the content of millions of books. Automating the analysis of texts can not only save time and resources, but also opens up new possibilities for studying the content of texts.

This lecture will introduce computational tools and methods to researchers and students in humanities disciplines. Papers and cases with advanced computational techniques and their applications in specific humanities disciplines, such as computational linguistics, network analysis, machine learning, text mining, tokenization and automated text parsing and various markup and advanced data-analysis strategies, will be studied and examined.

About the speaker:

Dr. Jeffrey R. Tharsen is a Computational Scientist for the Digital Humanities, Research Computing Center, Office of Research and National Laboratories, and a Lecturer in the Humanities and in the College, Humanities Division, Digital Studies Program at the University of Chicago.

As a practitioner of the digital and computational arts, in recent years Dr. Tharsen has been focusing on creating new methods and toolkits for a number of languages and traditions to help us better understand the classic works produced by some of our most ancient civilizations, how their contents and uses transformed over time, and how we can best employ these new methods to bring the lessons from the texts, their histories, and the cultures that produced them to modern audiences.

Dr. Tharsen’s research into the early development of Chinese literature and poetics utilizes a mix of cutting-edge linguistic strategies and traditional methodologies, mainly centered on philology, historiography, intellectual history, paleography, epigraphy and literary studies. Over the past decade, he has also been teaching and working in the nascent field of "digital humanities", focusing on digital philology and developing new types of systems for textual analytics, new data architectures and designing computational methodologies and frameworks for linguistic and textual analysis in a number of languages. In his position as university lead computational scientist for the digital humanities, he serves both as primary mentor to students interested in pairing humanities research methodologies with computational techniques, and as director of several teams of students and scholars, working to bring individualized research projects with digital and/or computational components to fruition and provide new insights into established disciplines.