Recommender systems in libraries

There has been an interesting exchange regarding the ‘bibtip’ recommender system on the NGC4LIB mailing list over the weekend. This explored some of the issues with recommender systems, specifically in the context of libraries, including ‘the ant problem’  – where recommender trails become self-perpetuating, the need for a critical mass of data for a successful recommender system, and the  need to base recommender systems on ‘high cost’ behaviour

This triggered a few thoughts on my part:

1. This is a difficult problem, and commercial organisations are willing to put significant resource into it. Would some library organisation (OCLC, Library consortiums, national or international groups of libraries) be interested in running a competition along the lines of the Netflix competition http://www.netflixprize.com/?

2. We would be in a much better position to build a critical mass of recommender (and other) information if we had a single source of bib records which acted as a hub for linking. OpenLibrary has a goal that might fulfil this, but Worldcat is clearly a good starting point as well. The library community really needs to exploit linking (creating a link seems to me to be a high(ish) cost behaviour). Wikipedia entries appear highly ranked in Google rankings and it must be partially related to it becoming a de facto standard for linking basic reference information – if we could emulate that so there was a central resource to which people ‘just linked’ when they cited bib information, then this would really start to exploit the latent information available in the web. (We are really late on this one, and have lots of catching up to do – I would guess Amazon must be the main receiver of ‘bib’ linking on the web currently).

On NGC4LIB Kevin Kidd said: “When it comes to things that really require critical mass – like tagging, reviews and ratings – we need to begin to develop platforms that can link users, usage and bib data across universities (I am really not qualified to comment on the needs of public libraries in this context). We have the technology now to begin doing this.”

I would argue all the technology is there, and has been for years. If there was a recognised hub of bib information which people used to link to, and tag (using existing bookmarking services like delicious, digg etc.), this would work right now – technology is simply not an issue. Being slightly less ambitious, the number of catalogues that offer the ability to easily bookmark a bib record without including session info in the URL is lamentable – which would be so simple from a technology perspective.

3. Just to highlight another approach to recommender systems, bX, developed by Herbert van de Sompel and others – this is an attempt to exploit user behaviour information gathered by OpenURL resolvers. I guess it will also be susceptible to some of the problems discussed on NGC4LIB, however, my guess is that this captures higher cost behaviour than looking at OPAC records.

Ex Libris Strategy Meeting

On Tuesday this week I attended a ‘Strategy Meeting’ organised by Ex Libris. This is an annual event in the UK in which Directors of library services using Ex Libris products meet with senior staff from Ex Libris, including the CEO Matti Shem Tov and Chief Strategy Officer Oren Beit Arie.

The day covered a lot of ground, so I’m going to summarise the main (in my view) points.

Just to start with the ‘company’ news – Julie Booth, the Managing Director of the UK office for the last 8 years is leaving the company – I think she will be missed by the UK customers, as she was a great person to work with, and willing to champion the UK customers within the company. Her responsibilities will be split between Robert Bley and Alan Oliver, who both currently work for the UK office.

The Ex Libris UK customer base now includes 96 institutions, and to some extent the turnout to the day seemed small in this context. On the otherhand, long gone are the days when the UK customers could all gather round a small table (which is how it was when I first started working with Ex L products)

Anyway, onto the more strategic issues…

The main two things from the day for me were:

The Open Platform Initiative

Ex Libris are committed to formalizing the open architecture of Ex Libris products to (in their words):

  • Allow maximum openness of products using standard interfaces and programming techniques and facilitate community collaboration
  • Enable customers to rely on robust products, while enjoying the already created open source components and developing additional ones

Essentially the reasoning behind this is that Libraries need tools to take more control over development and application of services and solutions. It is unrealistic for the vendor to do/provide everything for everybody.

By investing in open interfaces and service-based architectures, Ex Libris believes this enables customers or communities to work on enhancements, customisations, mashups etc.

Ex Libris want to have an open environment for community development and sharing, and a collaboration platform – a ‘marketplace’ for sharing community-built code.

The thing here, is that this is now going to be part of the core product development strategy – completely integral to the product, and used by Ex Libris in their own development (aka eating your own dog food)

There are already some examples of this approach paying off with the Primo product where a site has done an integration with Facebook, and another into a course management system. It is also clearly in the mind of Ex Libris that this is not just for Library staff/developers, but also for users themselves – that’s great news I think).

Ex Libris believe that social network activities (e.g. tagging, reviews etc.) are more likely to take place in context of a social network – so they are looking at working within social network grids, and expect to be able to make an announcement of a collaboration with a social network in the very near future. Also they are developing the ability to push tags etc. from Primo into existing social networks – so the users can work with their preferred service, even while working within the Primo environment.

Alongside other work in this area (The Berkley Accord from the ILS Discovery Interface Taskforce, and Jangle, kickstarted by Talis) this could really move us forward in bringing Library systems into the 21st Century and the collaborative approach encouraged by Web 2.0 thinking)

The URM

While we have seen a great deal of activity over the last 12-24 months on the ‘user’ facing aspects of library systems (Primo, VuFind, Encore, Arena, Scriblio, Endeca etc.), the systems running the back office tasks are still pretty much unchanged. In general the need to manage electronic resources has led to the introduction of new products (ERM, Verde, Project Xedio) and library staff are often still managing resources in multiple systems (plus many, many, spreadsheets in my experience)

Ex Libris propose to introduce a ‘Unified Resource Management’ framework that will encompass all resources managed by the library. I have to admit I’m not clear how much of what was said about this product was in commercial confidence, and how much I can openly blog. What we got on the day was an outline of the context and a diagram of the conceptual model. To get to this point Ex Libris have drawn on a number of reports including:

As well as carrying out interviews across the industry (and in the interests of full disclosure, I was one of the interviewees). I’ll have a chat with staff at Ex Libris and see how much more they are happy for me to share.

There was another announcement on the day that I thought was interesting, but unfortunately Ex Libris aren’t making this public at the moment, so I can’t share it with you – hopefully in the near future…