Taylor Arnold : A Pipeline for Exploration and Visualization of Textual Corpora

On The September 30, 2019

10h00  to 12h00
26, Place Bellecour - 69002 Lyon
Meeting room - Allée A - 1st floor

Exploratory research in the sciences and social sciences has increasingly turned to the analysis of large textual data sources. Common examples include electronic medical records, social media posts, online reviews, and digitized collections of books and periodicals.

Working with textual data, particularly from an exploratory perspective, poses many unique challenges that often go understudied in the fields of statistical computing and data visualization. In this talk, I walk through three case studies from my work in which difference visualization techniques are used to study and explore textual corpora. Issues of data privacy and multilingual corpora will be discussed. I will conclude by introducing the specific research I am focusing on in Lyon-the visualization of linguistic community formation in digital spaces-and how this relates to my larger research program.

Taylor Arnold is an assistant professor at the University of Richmond (Virginia, U.S.A.). He has an appointment within the linguistics program and the department of mathematics and computer science.