Developing recommendation services for a digital library with uncertain and changing data

ABSTRACT

In developing recommendation services for a new digital library called iLumina (www.ilumina-project.org), we are faced with several challenges related to the nature of the data we have available. The availability and consistency of data associated with iLumina is likely to be highly variable. Any recommendation strategy we develop must be able to cope with this fact, while also being robust enough to adapt to additional types of data available over time as the digital library develops. In this paper we describe the challenges we are faced with in developing a system that can provide our users with good, consistent recommendations under changing and uncertain conditions.

REFERENCES

• 1: McArthur, D., Giersch, S., Graves, B., Ward, C.R., Dillaman, R., Herman, R., Lugo, G., Reeves, J., Vetter, R., Knox, D., & Owen, S. (in press). Towards a Sharable Digital Library of Reusable Teaching Resources: Roles for Rich Metadata. Journal of Educational Resources in Computing.
• 2: Raymond J. Mooney , Loriene Roy, Content-based book recommending using learning for text categorization, Proceedings of the fifth ACM conference on Digital libraries, p.195-204, June 02-07, 2000, San Antonio, Texas, United States [doi>10.1145/336597.336662]
• 3: Paul Resnick , Hal R. Varian, Recommender systems, Communications of the ACM, v.40 n.3, p.56-58, March 1997 [doi>10.1145/245108.245121]
• 4: The IMS Global Learning Consortium, http://www.imsproject.org

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL

Additional Classification:
  H. Information Systems
  H.1 MODELS AND PRINCIPLES

General Terms:
Design, Documentation, Human Factors, Management, Performance, Theory

Keywords:
digital library, recommender system, user services