The APS Library is working on a recommendation system for special collections material. We're calling it PAL, for "People Also Liked".
Book recommendation systems are increasingly common, from Amazon to public library interfaces. However, for archives and special collections, such automated assistance has been rare. This is partly due to the the complexity of descriptions (EADs describing whole collections) and partly due to the complexity of the collections themselves (what is this collection “about”, and how is it related to another collection)?
The American Philosophical Society Library is using circulation data collected through the collection-management software package, Aeon, to automate recommendations. In our system, which we’re calling PAL, for People Also Liked, recommendations are offered in two ways: based on interests (“You’re interested in X, other people interested in X looked at these collections”) and on specific requests (“You’ve looked at Y, other people who looked at Y also looked that these collections”).
Try It Out
This site has examples for using PAL. To fully follow along, you'll need an account with our Aeon system. If you haven't yet, be sure to create an account.
The Interest-Based recommendations use user-supplied data. When registering to research at the APS, a user has the option to select from a list of 64 topics grouped into seven broad categories (Figure One). Though it's not mandatory, we do hope researchers use these options to let us konw what they're interested in, so that the library can better understand our users.
After registering, and upon signing in, a user sees a list of links (Figure Two); each link leads to a full page view (Figure Three) of collection recommendations. These recommendations take the model: “You’re interested in X, other people interested in X looked at these collections.”
PAL continues to be a work in progress. We hope to generalize our code for us at different institutions. We'd love your help. All code is on Github; if you're interested in talking more, please be in touch.
Early prototyping was done by Scott Ziegler. The majority of the code base was developed and refined by Richard Shrake. Ongoing development is being done by both Rich and Scott, with feedback, suggestions and testing by many wonderful people. All code is on Github, and we welcome thoughts and collaborations.
This website was put together by Scott Ziegler, using another great HTML5 Up template.
PAL is a project of the Center for Digital Scholarship at the American Philosophical Society.