Image Analysis for Archival Discovery (Aida)

The Aida research team explores applications of image analysis and machine learning in digital libraries of historic materials. We’re especially interested in what we might learn from the millions of digital images that librarians, archivists, and others are creating as they digitize the cultural record. We’re intrigued by the questions that machine learning approaches might help to surface in these collections and about our professional practices—and also by the questions our collections and professional practices might help to surface about machine learning.

Our current and recent efforts include “Digital Libraries, Intelligent Data Analytics, and Augmented Description: A Demonstration Project” (Library of Congress), “Extending Image Analysis for Archival Discovery” (IMLS, LG‐71‐16‐0152‐16), and “Oceanic Exchanges: Tracing Global Information Networks In Historical Newspaper Repositories, 1840-1914” (subaward on IMLS, LG-00-17-0104-17).

Code & Data

Code developed for our project is available via our GitHub organization page. See also the Exploring-ML-with-Project-Aida repository distributed by the Library of Congress.

Data generated for our project are made available through appropriate data repositories designed for long-term storage, preservation, and access. See our project page on the Open Science Framework: https://osf.io/xn7tv/

Documents, Publications, Presentations

• “Digital Libraries, Intelligent Data Analytics, and Augmented Description: A Demonstration Project,” final report delivered to the Library of Congress, 10 January 2020, rev. 15 June 2020
  • Final Presentation to the Library of Congress on Digital Libraries, Intelligent Data Analytics, and Augmented Description (presentation slides)
  • Virtual Wrap-Up Presentation: Digital Libraries, Intelligent Data Analytics, and Augmented Description (presentation slides)
  • Document Images and Machine Learning: A Collaboratory between the Library of Congress and the Image Analysis for Archival Discovery (Aida) Lab at the University of Nebraska, Lincoln, NE (presentation slides)
  • Work-in-Progress Reports Submitted to the Library of Congress as Part of Digital Libraries, Intelligent Data Analytics, and Augmented Description (narrative reports)
  • Code and code documentation for demonstration project explorations
• “Machine Learning in Research Libraries: A Snapshot of Projects, Opportunities, and Challenges,” panel presentation with Harish Maringanti, John Wang, and Elizabeth Lorang at CNI, December 2019
• “Application of the Image Analysis for Archival Discovery Team’s First- Generation Methods and Software to the Burney Collection of British Newspapers,” May 2019
  • Direct links to report, appendices, data, and code
• Interim report, submitted to Institute of Museum and Library Services, March 2019
• “Using Chronicling America’s Images to Explore Digitized Historic Newspapers & Imagine Alternative Futures,” National Digital Newspaper Program Annual Meeting, Washington, D.C., September 26, 2018
• “Patterns, Collaboration, Practice: Algorithms as Editing for Historic Periodicals,” American Antiquarian Society Spring Symposium 2018, Editorship as Collaboration: Patterns of Practice in Multi-Ethnic Periodicals, Worcester, MA, April 28, 2018
• Interim report, submitted to Institute of Museum and Library Services, February 2018
• “Increasing Our Vision for 21st-Century Digital Libraries,” Opening Keynote Presentation, HathiTrust Research Center UnCamp 2018, Berkeley, CA, January 25, 2018
• National Leadership Grant application, submitted to the Institute of Museum and Library Services, May 2016
• White paper, submitted to National Endowment for the Humanities, October 2016
• Final report, submitted to National Endowment for the Humanities, October 2016
• Interim report, submitted to National Endowment for the Humanities, January 2016
• “Developing an Image-Based Classifier for Detecting Poetic Content in Historic Newspaper Collections,” D-Lib Magainze, July 2015
• Interim report, submitted to National Endowment for the Humanities, June 2015
• Interim report, submitted to National Endowment for the Humanities, January 2015
• Extended abstract, Digital Humanities 2014
• Application for start-up funding, submitted to National Endowment for the Humanities, Office of Digital Humanities, September 2013

News & Updates

• All project materials related to “Digital Libraties, Intelligent Data Analytics, and Augmented Description” are publicly released (June 2020)
• The Aida team traveled to Washington, DC to present the final report to the Library of Congress for “Digital Libraties, Intelligent Data Analytics, and Augmented Description” (January 2020)
• With Harish Maringanti (University of Utah) and John Wang (Notre Dame), Liz Lorang participated in the “Machine Learning in Research Libraries: A Snapshot of Projects, Opportunities, and Challenges,” panel presentation at CNI (December 2019)
• “Digital Libraries, Intelligent Data Analytics, and Augmented Description: A Demonstration Project” featured in Nebraska Today (November 2019)
• Liz Lorang joins advisory board for Library of Congress’s Computing Cultural Heritage project (October 2019)
• Aida team requests/receives no-cost extension for “Extending Image Analysis for Archival Discovery” (IMLS, LG‐71‐16‐0152‐16) (September 2019)
• Leen-Kiat Soh presents on behalf of the Aida team at Machine Learning + Libraries summit (September 2019)
• Aida research team awarded research services contract from the Library of Congress for “Digital Libraries, Intelligent Data Analytics, and Augmented Description: A Demonstration Project” (July-November 2019)
• Aida team releases report, “Application of the Image Analysis for Archival Discovery Team’s First- Generation Methods and Software to the Burney Collection of British Newspapers” (May 2019)
• UVA and UNL team members hold working meeting in Washington, DC (September 2018)
• Team members present on Aida work on research with historic newspapers at annual meeting of the National Digital Newspaper Program in Washington, DC (September 2018)
• Aida co-directors Lorang and Soh present opening keynote for 2018 HathiTrust Research Center UnCamp (January 2018)
• Aida team members contribute to Digging into Data Challenge grant, “Oceanic Exchanges: Tracing Global Information Networks in Historical Newspaper Repositorires, 1840-1914,” and receive subaward to focus on image segementation of historic newspapers (May 2017).
• Aida team receives $462,000 in IMLS funding for their project “Extending Intelligent Computational Image Analysis for Archival Discovery” and welcome new team members from the University of Virginia! Read the Nebraska Today story (September 2016).
• UNL Annual Research Report for 2015 recognizes Aida! Read the article or view the video.
• “Developing an Image-Based Classifier for Detecting Poetic Content in Historic Newspaper Collections published in D-Lib Magainze, July 2015.
• Aida featured in Digital Americanists/Research Society for American Periodicals panel at American Literature Association (May 2015)
• Project team’s work featured on NET, Nebraska’s NPR Station. Listen to the story.
• Aida featured in UNL Today article (November 2014).
• Project directors Lorang and Soh present at 2014 Digital Library Federation Forum on early stages of Aida work