Paper Reading #19: From documents to tasks: deriving user tasks from document usage patterns

Comments:
Jaideep Balekar

Cindy Skach



Reference Info:

Title: From Documents to Tasks: Deriving User Tasks from Document Usage Patterns
Authors: Oliver Brdiczka
Conference: IUI '10 Proceedings of the 15th international conference on Intelligent 

  

Summary:

A knowledge worker is typically involved with multiple tasks and must switch often between them on a daily basis. The frequency of the switches between tasks become time expensive because of the recovery between tasks. Systems to aid users in switching exist but require too much from the user for their proper use. The paper proposes a system in which i automatically estimates a user's tasks from interactions with documents. The system focuses more on the document indentifiers rather than information contained within the document. The system monitors desktop activity and logs documents with focus on the desktop. Depending on their dwell time and similarity with other documents, frequencies and switches are estimated. The documents are then clustered according to the tasks.

 

Discussion:

I think it would be interesting to use such a system. I would like to have my tasks automated and switched for me to make it easier on me and more productive. I wonder if it would also group together unproductive things, or documents that may not be related to the work.