Predicting Document Access in Large Multimedia Repositories

Network-accessible multimedia databases, repositories, and libraries are proliferating at a rapid rate. A crucial problem for these repositories remains timely and appropriate document access. In this article, we borrow a model from psychological research on human memory, which has long studied retrieval of memory items based on frequency and recency rates of past item occurrences. Specifically, the model uses frequency and recency rates of prior document accesses to predict future document requests. The model is illustrated by analyzing the log file of document accesses to the Georgia Institute of Technology World Wide Web (WWW) repository, a large multimedia respository exhibiting high access rates. Results show that the model predicts document access rates with a reliable degree of accuracy. We describe extensions to the basic approach that combine the recency and frequency analyses and which incorporate respository structure and document type. These results have implications for the formulation of descriptive user models of information access in large repositories. In addition, we sketch applications in the areas of design of information systems and interfaces and their document-caching algorithms