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

Reference Information

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 typical knowledge worker is involved in multiple tasks and switches frequently between them every work day. These frequent switches become expensive because each task switch requires some recovery time as well as the reconstitution of task context. First task management support systems have been proposed in recent years in order to assist the user during these switches. However, these systems still need a fairly big amount of investment from the user side in order to either learn to use or train such a system.

In order to reduce the necessary amount of training, this paper proposes a new approach for automatically estimating a user’s tasks from document interactions in an unsupervised manner. While most previous approaches to task detection look at the content of documents or window titles, which might raise confidentiality and privacy issues, our approach only requires document identifiers and the temporal switch history between them as input.

The prototype system monitors a user’s desktop activities and logs documents that have focus on the user’s desktop by attributing a unique identifier to each of these documents. Retrieved documents are filtered by their dwell times and a document similarity matrix is estimated based on document frequencies and switches. A spectral clustering algorithm then groups documents into tasks using the derived similarity matrix. The described prototype system has been evaluated on user data of 29 days from 10 different subjects in a corporation. Obtained results indicate that the approach is better than previous approaches that use content.

(Figure 1: Average precision, recall and F-measure with respect

to the number of user tasks)

Discussion

This paper was pretty technical. The authors, no doubt, comes from a highly technical background and his writing reflects this fact. However, I has taken the information storage and retrieval class last semester and I am quite familiar with the terms - clustering, F-measure, precision, recall, etc. that he uses in the paper. I think this system will be very useful since we switch between numerous tasks multiple times each day. Software like this would significantly improve work efficiently and reduce the downtime caused due to task switching.