User interactions with everyday applications as context for just-in-time information access
Proceedings of the 5th international conference on Intelligent user interfaces
TaskTracer: a desktop environment to support multi-tasking knowledge workers
Proceedings of the 10th international conference on Intelligent user interfaces
Personalizing search via automated analysis of interests and activities
Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval
A session based personalized search using an ontological user profile
Proceedings of the 2009 ACM symposium on Applied Computing
Tell me more, not just "more of the same"
Proceedings of the 15th international conference on Intelligent user interfaces
Hi-index | 0.00 |
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.