USER: User-sensitive expert recommendations for knowledge-dense environments

Abstract

Traditional recommender systems tend to focus on e-commerce applications, recommending products to users from a large catalog of available items. The goal has been to increase sales by tapping into the user's interests by utilizing information from various data sources to make relevant recommendations. Education, government, and policy websites face parallel challenges, except the product is information and their users may not be aware of what is relevant and what isn't. Given a large, knowledge-dense website and a non-expert user searching for information, making relevant recommendations becomes a significant challenge. This paper addresses the problem of providing recommendations to non-experts, helping them understand what they need to know, as opposed to what is popular among other users. The approach is user-sensitive in that it adopts a 'model of learning' whereby the user's context is dynamically interpreted as they browse and then leveraging that information to improve our recommendations. © Springer-Verlag Berlin Heidelberg 2006.