Search CALO Publications:

Author and Title
Shen, J., Li, L., Dietterich, T., Herlocker, J. A Hybrid Learning System for Recognizing User Tasks from Desktop Activities and Email Messages. In 2006 International Conference on Intelligent User Interfaces, 86-92. Sydney, Australia.

Abstract
The TaskTracer system seeks to help multi-tasking users
manage the resources that they create and access while car-
rying out their work activities. It does this by associating
with each user-de ned activity the set of les, folders, email
messages, contacts, and web pages that the user accesses
when performing that activity. The initial TaskTracer sys-
tem relies on the user to notify the system each time the user
changes activities. However, this is burdensome, and users
often forget to tell TaskTracer what activity they are work-
ing on. This paper introduces TaskPredictor, a machine
learning system that attempts to predict the user's current
activity. TaskPredictor has two components: one for general
desktop activity and another speci cally for email. TaskPre-
dictor achieves high prediction precision by combining three
techniques: (a) feature selection via mutual information, (b)
classi cation based on a con dence threshold, and (c) a hy-
brid design in which a Naive Bayes classi er estimates the
classi cation con dence but where the actual classi cation
decision is made by a support vector machine. This paper
provides experimental results on data collected from Task-
Tracer users.

Download