LC Labs Letter: November 2019


A Monthly Roundup of News and Thoughts from the Library of Congress Labs Team

Concordia Featured in Code 4 Lib

The By the People team shared their experience developing Concordia with Agile in an article published in Code4Lib Journal. The articles describes the By the People program, how the team adopted an Agile approach, and the process of developing Concordia.

We hope the discussion demonstrates the ways we designed opportunities for public audiences to engage with Library resources. The piece also addresses the ways design considerations were used to align the tool with the technical approaches and requirements of the Library of Congress and the design to allow Concordia to scale and adapt to new collections and user needs. Read the article here:

Computing Cultural Heritage in the Cloud: Quarterly Update

If you’d like to hear an update on the Mellon-funded Computing Cultural Heritage in the Cloud project, please join us for our first online info session where we’ll give a brief overview of the grant, describe the progress to date, and answer questions about upcoming opportunities.

The call will take place on Friday, December 13, 1pm – 2pm Eastern. To register, please visit:

University of Nebraska-Lincoln: “Digital Libraries, Intelligent Data Analysis, and Augmented Description: A Demonstration Project”

This month, the Project AIDA team at the University of Nebraska-Lincoln presented on their project “Digital Libraries, Intelligent Data Analysis, and Augmented Description.” This collaboration with LC Labs demonstrates five possible applications of machine learning to improve the services, collections access, and discoverability of the Library of Congress.

Drs. Liz Lorang, Leen-Kiat Soh, and doctoral candidates Mike Pack and Yi Lee will spend the final 1-2 months of the project testing five ideas for further exploration. They are: 1) informed crowdsourcing for labeling the documents in a training set, 2) enriched metadata through tags, 3) benchmarked datasets for documents, 4) low-cost ground-truthing using weak supervision, and 5) the application of deep learning to Library-related tasks.

When released, the final white paper documenting their results and process will be made publicly available and shared via the newsletter.

By the People: Veteran’s Day Challenge Update

On Wednesday, November 6, By the People kicked off a Veterans Day Challenge – asking volunteers to both transcribe and review Samuel J. Gibson’s 200-page Civil War POW diary by the end of the holiday. Volunteers leapt into action and met the goal in less than 36 hours! With the holiday still a few days away, we set a stretch goal to review “Civil War Soldiers: ‘Disabled but not disheartened”, in which volunteers completed 371 additional pages. This campaign features writings by Union soldiers who lost their right arms in the conflict and entered a left-handed penmanship competition. In addition to moving these documents of service and sacrifice across the finish line, the challenge encourages volunteers to engage deeply with these histories in honor of all who have served.


  • LC Labs attended the Association of Moving Image Archivists Conference (AMIA) 2019 on Thursday, November 14 and the Coalition of Network Information (CNI) Annual Meeting on December 9 & 10
  • We are hiring two 2020 Junior Fellows! Please share this information widely with interested candidates. Applications close 12/20/19.
  • Sweater News: a publication dedicated almost exclusively to covering trends in plush pullovers. Only one of the amazing findings at the Library’s Art + Design Night that took place on Friday, November 8. See what else people found by searching #TouchTheBooks on social media.
  • Looking for some fun, instructive reading? You can read Open a GLAM Lab, co-authored by Labs member Abbey, for free here. Read more about Abbey’s experience participating in the book sprint in this blog post.

Kate’s Corner
Notes from the Director of Digital Strategy

Fall is upon us here in D.C., and we’ve been enjoying sunny days and brilliant displays from the changing leaves. It’s always a season of reflection for me, and this year especially so as we move forward with new plans, while looking back at what we’ve achieved so far.

We recently celebrated the one-year anniversary of our By the People crowdsourcing program here at the Library, and completed a Veterans Day challenge in record time. I’m so proud of the work our team has done building a software platform and rolling out collections from the “Angel of the Battlefield,” Clara Barton to the “Man Who Recorded the World,” Alan Lomax. I’m delighted by how this project has invited the people into the Library of Congress in unprecedented ways—to explore, to learn, and to grow.

All of this makes me excited to think about our big tent, and the possibilities for bringing people together. I hope you’ll have a chance to join us!

-Kate Zwaard

For more information about LC Labs, visit us at
Questions? Contact LC Labs at [email protected]
Sign up to regularly receive our monthly newsletter at //

Introducing the Computing Cultural Heritage in the Cloud Project

With support from the Andrew W. Mellon Foundation, the LC Labs team will pilot ways to combine cutting edge technology and the collections of the largest library in the world, to support creative new uses of collections. This project will explore service models to support researchers accessing Library of Congress collections in the cloud, with findings shared throughout the 2 year project.

In the Library’s Web Archives: 1,000 U.S. Government PowerPoint Slide Decks

The Digital Content Management section has been working to extract and make available sets of files from the Library’s significant Web Archives holdings. The outcome of the project is a series of web archive file datasets, each containing 1,000 files of related media types selected from .gov domains. You can read more about this series […]

What can you find in 1.7 million phone book images?

The Digital Content Management Section (DCM) is excited to announce the release of over 1.7 million images scanned from the Library of Congress U.S. Telephone Directory Collection. These images originate from thousands of reels of black and white microfilm held in the Main Reading Room – now available on the Library’s website. The process for getting […]