[Asis-l] Computer Science Seminar: Dr. Bob Allen: What to do with Millions of Pages of Digitized Historical Newspapers?

[David Langstroth]

Faculty of Computer Science
6050 University Avenue
Dalhousie University
Halifax, NS, Canada



                       COMPUTER SCIENCE SEMINAR



Speaker:   Dr. Bob Allen
           Drexel University, Philadelphia

Title:     What to do with Millions of Pages of Digitized
           Historical Newspapers?

Date:      Friday April 24, 2009

Time:      11:30 a.m.

Location:  Jacob Slonim Conference Room (430)
           6050 University Ave., Halifax, NS, Canada

Note:      Coffee and cookies will be provided, courtesy of Faculty of
           Computer Science.


Abstract:

Mass digitization projects are producing vast collections of
humanities-related materials. For example National Digital Newspaper
Program in the US is digitizing newspapers which were printed 1880 to 
1922. Although the quality is highly variable, the page images are OCRd,
indexed, and made available to the public through a search engine. We
describe projects which go beyond simple indexing to mine the rich and 
varied content of the newspapers. Ultimately, the historical events
reported in the newspapers could be coordinated with other historical
resources and made widely accessible through interfaces such as
interactive timelines.


Short Biography:

Bob Allen has extensive research and professional experience on digital
libraries and information retrieval. He developed the basic algorithms
for recommender systems. Dr. Allen was the Editor-in-Chief of the ACM
Transactions on Information Systems, and was Chair of the ACM
Publications Board. He currently has a grant for developing a curriculum
on the management of digital information and he is writing a
comprehensive textbook: Information Science and Systems.


Speaker URL:
http://www.ischool.drexel.edu/faculty/ballen/


Host contact: Mike Shepherd <shepherd at cs.dal.ca>