Extending Low Level Context Events by Data Aggregation
Key: Lok08-3
Author: Robert Lokaiczyk, Manuel Görtz
Date: September 2008
Kind: In proceedings
Book title: 8th International Conference on Knowledge Management (IKNOW '08), Special Track on User Context and User Models (UCUM)
Keywords: 2008 APOSDLE SAP context e-learning lang:en myOwn
Abstract: Providing context-aware personalized desktop assistance that is related to the work task of the knowledge worker is a recent research topic. Our approach focuses on task detection by work context observation. A sum of steps towards this goal are addressed by our work, including (1) accessing the desktop computers event stream of user interaction and system status, (2) context reasoning and prediction of the user's working task and (3) recommending relevant resources based on the predicted work goal. Here, we present an algorithmic approach for automated context aggregation by using mapping functions. This instance of context inference combines lower-level context features to new aggregated features which represent a higher-level context. While related work uses manually defined domain-specific rules for combining features, we automate this approach and in addition show that by means of that the prediction accuracy of the user's work task increases significantly.

The documents distributed by this server have been provided by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, not withstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.