Jo Guldi: Towards a Practice of Text Mining to Understand Change Over Historical Time
Jo Guldi: Towards a Practice of Text Mining to Understand Change Over Historical Time

Jo Guldi: Towards a Practice of Text Mining to Understand Change Over Historical Time

Haidy Moussa

99 min
Success & Inspiration
Play

Description

<p>Recorded on March 8, 2023, this video features a lecture by Jo Guldi, Professor of History and Practicing Data Scientist at Southern Methodist University. Professor Guldi’s lecture was entitled “Towards a Practice of Text-Mining to Understand Change Over Historical Time: The Persistence of Memory in British Parliamentary Debates in the Nineteenth Century.”</p> <p>Co-sponsored by Social Science Matrix, the UC Berkeley Department of History, and D-Lab, this talk was presented as part of the <a href= "https://matrix.berkeley.edu/category/event-type/social-science-and-data-science/"> Social Science / Data Science event series</a>, a collaboration between Social Science Matrix and D-Lab.</p> <h3>Abstract</h3> <p>A world awash in text requires interpretive tools that traditional quantitative science cannot provide. Text mining is dangerous because analysts trained in quantification often lack a sense of what could go wrong when archives are biased or incomplete. Professor Guldi’s talk reviewed a brief catalogue of disasters created by data science experts who voyage into humanistic study. It finds a solution in “hybrid knowledge,” or the application of historical methods to algorithm and analysis.</p> <p>Case studies engage recent work from the philosophy of history (including Koselleck, Erle, Assman, Tanaka, Chakrabarty, Jay, Sewell, and others) and investigate the “fit” of algorithms with each historical frame of reference on the past. This talk profiles recent research into the status of “memory” in British politics. It profiled the persistence of references to previous eras in British history, to historical conditions per se, and to futures hoped for and planned, using NLP analysis. It presented the promise and limits of text-mining strategies such as Named Entity Recognition and Parts of Speech Analysis for modeling temporal experience as a whole, suggesting how these methods might support students of social science and the humanities, and also revealing how traditional topics in these subjects offer a new rese

Uploader

precious_sky

precious_sky

Jo Guldi: Towards a Practice of Text Mining to Understand Change Over Historical Time - Listen Free | WowFM