ePADD version 8 now available

The ePADD development team is excited to announce the release of version 8!

ePADD is free and open source software developed by Stanford Libraries' Special Collections & University Archives that uses natural language processing and machine learning to support archival appraisal, processing, discovery, and delivery for email of historical or cultural value.

Improved Performance for Large Collections

This new version includes strategic updates to improve ePADD’s performance for very large email collections of up to 2 million messages. Our goal was to make sure that as users navigated through ePADD, reviewing and appraising a collection, that they would not encounter any significant delays in loading. The software developers’ approach to accomplish this goal included simplifying the processes that take place when loading a collection and offsetting certain computations from within the application to the initial loading of the application.

New Entity Model

ePADD identifies, extracts, and manages entities using a custom natural language processing toolkit. The extracted entities include persons, fine-grained entities such as corporations and government agencies, as well as other entity types such as diseases, awards, and events. This
new version of the software includes a simplified entity recognition model, that significantly decreases the time that it takes to import a collection into ePADD. This model is also more extensible which will benefit future software developers working with the application code.

Final Version of Phase III

This version is the last that will be released as part of our Andrew W. Mellon Foundation grant funded project. We began this phase of the project in January, 2020, and despite facing our share of pandemic related challenges, we still managed to accomplish all of our goals with some creative problem solving.

Many thanks to everyone who has contributed to this project phase: our software development team, Sudheendra Hangal, Chinmay Narayan, and Chaiyasit Manovit; the Stanford advisory group, Glynn Edwards, Michael Olson, and Annie Schweikert; our project partners at Harvard University and the University of Manchester, Stephen Abrams, Tricia Patterson, Ian Gifford, Jessica Smith, and Jochen Farwer; the ePADD Discovery Working Group, Callum McKean, Alix Norton, Michael Olson, Tricia Patterson, Jonathan Pledge, Jessica Smith, and Christina Velazquez Fidler.