The document discusses the implications of recommender systems in scholarly communication, particularly focusing on how user-generated content and usage data can enhance information discovery. It emphasizes the need for recommender services that concentrate on scholarly materials, utilizing data mining techniques to generate relevant recommendations based on user activity. Additionally, it highlights the benefits and growing importance of these systems in managing information overload and facilitating user engagement in research.

1. Recommendations
and the Library
Nettie Lagace
Product Manager, Ex Libris

2. Copyright Statement
All of the information and material inclusive of text, images, logos, product names is either the
property of, or used with permission by Ex Libris Ltd. The information may not be distributed,
modified, displayed, reproduced – in whole or in part – without the prior written permission of
Ex Libris Ltd.
TRADEMARKS
Ex Libris, the Ex Libris logo, Aleph, SFX, SFXIT, MetaLib, DigiTool, Verde, Primo, Voyager,
MetaSearch, MetaIndex, bX and other Ex Libris products and services referenced herein are
trademarks of Ex Libris, and may be registered in certain jurisdictions. All other product names,
company names, marks and logos referenced may be trademarks of their respective owners.
DISCLAIMER
The information contained in this document is compiled from various sources and provided on an
"AS IS" basis for general information purposes only without any representations, conditions or
warranties whether express or implied, including any implied warranties of satisfactory quality,
completeness, accuracy or fitness for a particular purpose.
Ex Libris, its subsidiaries and related corporations ("Ex Libris Group") disclaim any and all liability
for all use of this information, including losses, damages, claims or expenses any person may
incur as a result of the use of this information, even if advised of the possibility of such loss or
damage.
© Ex Libris Ltd., 2009

3. Agenda
• What will the future be like?
• Recommender systems in general
• “In the Wild”
• New scholarly environments
• Article recommenders
• Interfaces
• Contributions

4. http://www.idealog.com/stay-ahead-of-the-shift-
what-publishers-can-do-to-flourish-in-a-community-centric-web-world

5. Recommender Systems
Recommender systems form a specific type of information
filtering (IF) technique that attempts to present information
items (movies, music, books, news, images, web pages, etc.)
that are likely of interest to the user.
http://en.wikipedia.org/wiki/Recommendation_systems

16. Library Book Recommendations

18. http://library.hud.ac.uk/data/usagedata/

19. Changes in Scholarly Communication
• Greater focus on content users create and
choices & preferences they make
• User contribution increasingly important
• Contributed explicitly by individuals
• The Web is multi-directional

20. Changes in Scholarly Communication
• Greater focus on content users create and
choices & preferences they make
• User contribution increasingly important
• Contributed explicitly by individuals
• Implicitly - usage data captured by the
system (‘clickstreams’)
• The Web is multi-directional

21. There is a need
• Information overload calls for new tools
that assist users in finding relevant
information
• Useful in the context of:
• learning
• exploring new fields of interest
• inter-disciplinary work
• specific information needs that are
outside one’s field of expertise
• Search is NOT the only way to find…

22. Scholarly Recommender Service
Need to:
• Focus on scholarly materials – particularly
articles (core unit of use)
• Be based on structural analysis of usage and
not just based on popularity

25. CiteULike Recommendations
/embedded video removed from PPT – see
http://www.youtube.com/watch?v=ium2fS1LW5w

27. What is bX?
• A service which taps into the power of the
networked scholarly community to
generate recommendations based on
article usage
• Based on data mining and structural
analysis of aggregated usage data,
across libraries and scholarly information
environments
• Massive repository of user data -
growing
• Derives from research done at Los
Alamos National Laboratory by Johan
Bollen and Herbert Van de Sompel

28. Interest in usage-based measures
• COUNTER – www.projectcounter.org
• SUSHI - www.niso.org/workrooms/sushi
• JISC MOSAIC – www.sero.co.uk/jisc-mosaic.html
• Metrics for scholarly evaluation:
• UKSG Usage Factors project
- uksg.org/usagefactors
• Project MESUR - www.mesur.org

29. Implicit user contribution
• Circulation data
• Clickstreams, recording a search process
• Actions
• Item viewed
• Item downloaded
• Item sent
• Item bookmarked
• Item printed
• Item stored

31. Potential uses of implicit contribution
• Collection development
• Evaluation
• Trend analysis
• Relevance ranking
• Recommendations

32. bX Demo

33. bX Demo

34. bX Demo

35. bX Demo

36. bX Demo

37. Link resolver usage logs
• A good basis:
• Represent users’ information-seeking paths
in a standardized way
• Are across information providers
• Are across institutions
• There are a lot of them

38. Link resolver usage paths
E-journal
publisher
site
E-journal E-Book
publisher OpenURL publisher
site site
Google OpenURL Link OpenURL Library
Scholar Resolver interface
OpenURL
A&I Document
databases Delivery
Citation
databases

39. Built on OpenURL
• Usage data –OpenURL context objects-- is
harvested from link resolver logs through OAI-PMH
• Build a (very large) aggregate of usage data
• Mine the aggregate to derive scholarly
recommender services: a structure describing
relationships between scholarly materials is created
• bX receives OpenURL requests
• A list of recommended materials is generated per
request
• open interface - accessible via API
• viewable via SFX menu, other discovery
interfaces

40. Bollen J, Van de Sompel H, Hagberg A, Bettencourt L, Chute R, et al. (2009)
Clickstream Data Yields High-Resolution Maps of Science.
PLoS ONE 4(3): e4803. doi:10.1371/journal.pone.0004803

41. bX Research
rbertv/ .pdf
o v/he version
.lanl.g pted_
p ublic _acce
ht tp:// jcdl06
pa pers/

42. More about the interaction with bX
• Request to bX is sent through an API
• Results are returned as
• XML (default)
• Text
• ATOM
• RSS

43. Recommendations in Primo V3

46. Benefits of bX Contribution
• Ongoing analysis of SFX
usage data created by
library users
• Continual improvement of
recommendations
• Cooperation with other
research library sites – on a
grand scale

47. What do people say?
“JSTOR meets Amazon!?”
- ELUNA twitterer
“On May 5, Ex Libris rolled out the shiny new fabulousness
that is bX. … (turns) the Services Menu into a point-of-
need discovery tool. I think this is awesome. ”
- Jamene Brooks-Kieffer, Kansas State Univ.
“I found exactly what I wanted. I've already found even more relevant
articles in 10 minutes than I've found in the last 10 months using more
traditional methods of research.”
- Ph.D. student, Arizona State University
“I’m always trying to find new connections between biological systems. This
looks like a really useful tool for this discovery. I’m interested in seeing
others’ connections. An unknown system can link to one which is well-
studied.”
- Laboratory director, University of Ottawa Heart Institute
“One thing I've noticed and got a few comments about is that the increase in
amount of recommendations has been noticeable from last summer to
now. Now it's much easier (to find recommendations). The recommendations
seem … relevant”
- Systems librarian, FinELib

48. “The Web, they say, is leaving the era of
search and entering one of discovery.
What's the difference? Search is what you
do when you're looking for something.
Discovery is when something wonderful
that you didn't know existed, or didn't
know how to ask for, finds you.“
Jeffrey M. O’Brien, "The race to create a 'smart' Google“
http://money.cnn.com/magazines/fortune/fortune_archive/
2006/11/27/8394347/

49. Thank you!
nettie.lagace@exlibrisgroup.com