PersonalWeb: an extensible framework to recommend web and personal information

ABSTRACT

The large amount of information spread out among applications raised several challenges when trying to retrieve it, as information useful in the past is potentially useful in the future. Most recommender systems resort to contextual information to provide single-source document suggestions, disregarding the manifold Personal Information (PI) sources. We believe that PI can provide a richer background of the user's interests, providing personally-relevant and user-centered suggestions. In this paper, we describe an extensible framework that makes use of both contextual and personal information to provide recommendations that are relevant to the user and the task at hand, instead of only the latter. Herein we also present a preliminary evaluation of our framework still mostly based on contextual information. This pilot study presented satisfying results disambiguating contexts, suggesting web and personal documents and dealing with context changes, paving the way to its enrichment with more PI sources.

References

1. Budzik, J. and Hammond, K. J. User interactions with everyday applications as context for just-in-time information access. In Proc of IUI, ACM (2000).
2. Daoud, M. et al. A session based personalized search using an ontological user profile. In Proc. of Symposium on Applied Computing, ACM Press (2009).
3. Dragunov, A. N. et al. TaskTracer: a Desktop Environment to support multi-tasking knowledge workers. In Proc. of IUI, ACM (2005).
4. Barata, G. Blaze: Automating User Interaction in Graphical User Interfaces. Master Thesis at Instituto Superior Técnico (2009).
5. Iacobelli, F. et al. Tell Me More, not just "More of the Same". In Proc. of IUI, ACM Press (2010).
6. Jones, W. Finders, keepers? The present and future perfect in support of personal information management. First Monday, 9 (2004).
7. Marshall, C. C. and Jones, W. Keeping encountered information, pages 66--67. ACM (2006).
8. Sieg, A., Mobasher, B., Lytinen, S. and Burke, R. Using concept hierarchies to enhance user queries in web-based information retrieval. In Proc. of ICAIA (2004).
9. Teevan, S. T. Dumais, and E. Horvitz. Personalizing Search via Automated Analysis of Interests and Activities. In Proc. of Research and Development in Information Retrieval, ACM Press, (2005).
10. Teevan, J. et al. How people find personal information. Personal Information Management, chapter 2, University of Washington Press (2007).

Index Terms

• Information systems

  • Information retrieval

  • Information storage systems