Now showing items 41-45 of 45
Scalable Content-Based Analysis of Images in Web Archives with TensorFlow and the Archives Unleashed Toolkit
We demonstrate the integration of the Archives Unleashed Toolkit, a scalable platform for exploring web archives, with Google's TensorFlow deep learning toolkit to provide scholars with content-based image analysis ...
The Archives Unleashed Notebook: Madlibs for Jumpstarting Scholarly Exploration
This paper introduces the Archives Unleashed Notebook, which is designed to work with derivative datasets from the Archives Unleashed Cloud, a platform for analyzing web archives. These datasets contain common starting ...
Warclight: A Rails Engine for Web Archive Discovery
This paper describes the development of Warclight, a portmanteau of the open-source Blacklight platform and the ISO-standard Web ARChive file format. Warclight allows users to explore web archives that have been indexed ...
Building Community and Tools for Analyzing Web Archives through Datathons
Starting in March 2016, the Archives Unleashed team and our collaborators have brought together social scientists, humanists, archivists, librarians, computer scientists, and other stakeholders to explore web archives as ...
Web Archives Analysis at Scale with the Archives Unleashed Cloud
Web archives, repositories of born-digital information dating back to the Internet Archive and national libraries in the mid-1990s, are fantastic resources of information covering topics of interest to humanities and social ...