Activity-based serendipitous recommendations with the Magitti mobile leisure guide
This paper presents a context-aware mobile recommender system, codenamed Magitti. Magitti is unique in that it infers user activity from context and patterns of behavior and, without its user having to issue a query, generates matching recommendations for suitable leisure activities. Extensive field studies of leisure time practices in an urban setting (Tokyo) motivated the idea and shaped the details of its design. Magitti filters a large database of city-guide-style leisure information to find the most relevant items based on the user's profile, history, context, and predicted activity. The paper describes the fieldwork, user interface, system components, and evaluation of the Magitti prototype.
Bellotti, V. ; Begole, J. ; Chi, E. H. ; Ducheneaut, N. ; Fang, J. ; Isaacs, E. ; King, T. H. ; Newman, M. ; Partridge, K .; Price, R. ; Rasmussen, P. ; Roberts, M. ; Schiano, D. J. ; Walendowski, A. Activity-based serendipitous recommendations with the Magitti mobile leisure guide. Proceedings of the 26th Annual ACM Conference on Human Factors in Computing Systems (CHI 2008); 2008 April 5-10; Florence; Italy. NY: ACM; 2008; 1157-1166.