Recommender Systems try to assist users to access complex information spaces regarding their long term needs and preferences. Various recommendation techniques have been investigated and each one has its own strengths and weaknesses. Especially, content-based techniques suffer of overspecialization problem. We propose to inject diversity in the recommendation task by exploiting the content-based user profile to spot potential surprising suggestions. In addition, the actual selection of serendipitous items is motivated by an applicative scenario. Thus, the reference scenario concerns personalized tours in a museum and serendipitous items are introduced by slight diversions on the context-aware tours. © 2011 Springer-Verlag Berlin Heidelberg.
CITATION STYLE
Iaquinta, L., De Gemmis, M., Lops, P., Semeraro, G., & Molino, P. (2011). Motivating serendipitous encounters in museum recommendations. In Studies in Computational Intelligence (Vol. 361, pp. 159–167). https://doi.org/10.1007/978-3-642-21384-7_11
Mendeley helps you to discover research relevant for your work.