Detecting and correcting user activity switches: algorithms and interfaces

The TaskTracer system allows knowledge workers to define a set of activities that characterize their desktop work. It then associates with each user-defined activity the set of resources that the user accesses when performing that activity. In order to correctly associate resources with activities and provide useful activity-related services to the user, the system needs to know the current activity of the user at all times. It is often convenient for the user to explicitly declare which activity he/she is working on. But frequently the user forgets to do this. TaskTracer applies machine learning methods to detect undeclared activity switches and predict the correct activity of the user. This paper presents TaskPredictor2, a complete redesign of the activity predictor in TaskTracer and its notification user interface. TaskPredictor2 applies a novel online learning algorithm that is able to incorporate a richer set of features than our previous predictors. We prove an error bound for the algorithm and present experimental results that show improved accuracy and a 180-fold speedup on real user data. The user interface supports negotiated interruption and makes it easy for the user to correct both the predicted time of the task switch and the predicted activity.

[1]  Thomas G. Dietterich,et al.  Fewer clicks and less frustration: reducing the cost of reaching the right folder , 2006, IUI '06.

[2]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.

[3]  Andrea Bunt,et al.  Matching attentional draw with utility in interruption , 2007, CHI.

[4]  Dennis Quan.  Haystack : Metadata-Enabled Information Management , 2003 .

[5]  Thomas G. Dietterich,et al.  TaskTracer: a desktop environment to support multi-tasking knowledge workers , 2005, IUI.

[6]  Victor Kaptelinin,et al.  UMEA: translating interaction histories into project contexts , 2003, CHI '03.

[7]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[8]  Mary Czerwinski,et al.  A diary study of task switching and interruptions , 2004, CHI.

[9]  Koby Crammer,et al.  Online Passive-Aggressive Algorithms , 2003, J. Mach. Learn. Res..

[10]  Thomas G. Dietterich,et al.  A hybrid learning system for recognizing user tasks from desktop activities and email messages , 2006, IUI '06.

[11]  Thomas G. Dietterich,et al.  Real-Time Detection of Task Switches of Desktop Users , 2007, IJCAI.

[12]  Ian Smith,et al.  Taking email to task: the design and evaluation of a task management centered email tool , 2003, CHI '03.

[13]  Thorsten Joachims,et al.  Learning to classify text using support vector machines - methods, theory and algorithms , 2002, The Kluwer international series in engineering and computer science.

[14]  Mary Czerwinski,et al.  GroupBar: The TaskBar Evolved , 2003 .

[15]  Li-Te Cheng,et al.  Activity Explorer: Activity-centric collaboration from research to product , 2006, IBM Syst. J..