University of Toronto researchers have developed statistical computer techniques for dating historical documents. The method involves a subset of about 10,000 charters that are dated and to look for changes in language over time that could be used to date other documents. The analysis also seeks out patterns in the number of times specific words are used.
"Our goal is to develop algorithms to help automate the process of estimating the dates of undated charters through purely computational means," the researchers say. They test the patterns by attempting to date individual documents in a set. The most successful approach so far is known as the maximum prevalence technique, which is a statistical strategy that produces a most probable date by comparing the set of words in the document with the distribution of the training set. The researchers say the same technique could be used to identify the author and to eliminate forgeries.
From Technology Review
View Full Article
Abstracts Copyright © 2013 Information Inc., Bethesda, Maryland, USA
No entries found