A Study on Automatic Classification of Users’ Desktop Interactions

Knowledge workers frequently change activities, either by choice or through interruptions. With an increasing number of activities and activity switches, it is becoming more and more difficult for knowledge workers to keep track of their desktop activities. This article presents our efforts to achieve activity awareness through automatic classification of user's everyday desktop activities. For getting a deeper understanding, we investigate performance of various classifiers with respect to discriminative power of time-, interaction-, and content-based feature sets for different work scenarios and users. Specifically, by viewing an activity as a sequence of desktop interactions we present (1) a methodology for translating a user's desktop interactions into activities, (2) evaluation of the discriminative power of different activity features and feature types, and (3) analysis of supervised classification models for classifying desktop activity under two different scenarios, i.e., an activity-centric scenario and a user-centric scenario. The experiments are carried out on a real-world dataset, and the results show satisfactory accuracy using relatively few and simple types of features.

[1]  Eric Horvitz,et al.  The Lumière Project: Bayesian User Modeling for Inferring the Goals and Needs of Software Users , 1998, UAI.

[2]  Andreas S. Rath,et al.  Machine Learning based Work Task Classification , 2009, J. Digit. Inf. Manag..

[3]  Adrian Williamson,et al.  Moneypenny: Lessons from the Messy Desk , 1998, Interact. Comput..

[4]  Tom Fawcett,et al.  Activity monitoring: noticing interesting changes in behavior , 1999, KDD '99.

[5]  Eric Horvitz,et al.  Attention-Sensitive Alerting , 1999, UAI.

[6]  Eric Horvitz,et al.  Learning and reasoning about interruption , 2003, ICMI '03.

[7]  Daniel H. Grollman,et al.  Astrology: The Study of Astro Teller , 2004 .

[8]  H. Yanco,et al.  Automation as Caregiver: A Survey of Issues and Technologies , 2003 .

[9]  Pedro M. Domingos,et al.  Programming by Demonstration Using Version Space Algebra , 2003, Machine Learning.

[10]  Carl Gutwin,et al.  KEA: practical automatic keyphrase extraction , 1999, DL '99.

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

[12]  Kurt D. Fenstermacher.  Revealed Processes in Knowledge Management , 2005, Wissensmanagement.

[13]  Duen-Ren Liu,et al.  Task-stage knowledge support: coupling user information needs with stage identification , 2005, IRI -2005 IEEE International Conference on Information Reuse and Integration, Conf, 2005..

[14]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques with Java implementations , 2002, SGMD.

[15]  Klaus Tochtermann.  Personalization in Knowledge Management , 2002, Metainformatics.

[16]  Arne Beckhaus,et al.  Enhancing Just-in-Time E-Learning Through Machine Learning on Desktop Context Sensors , 2007, CONTEXT.

[17]  Mary Czerwinski,et al.  RelAltTab: assisting users in switching windows , 2008, IUI '08.

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

[19]  Jacek Gwizdka,et al.  Individual differences and task-based user interface evaluation: a case study of pending tasks in email , 2004, Interact. Comput..

[20]  Luca Costabello,et al.  Time Based Context Cluster Analysis for Automatic Blog Generation , 2008 .

[21]  Oliver Brdiczka,et al.  Temporal task footprinting: identifying routine tasks by their temporal patterns , 2010, IUI '10.

[22]  Ling Chen,et al.  BUILDING USER TASK SPACE BY MINING TEMPORALLY PROXIMATE DESKTOP ACTIONS , 2011, Cybern. Syst..

[23]  Manuel A. Pérez-Quiñones,et al.  An integrative approach to requirements analysis: How task models support requirements reuse in a user-centric design framework , 2009, Interact. Comput..

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

[25]  Duen-Ren Liu,et al.  Mining and Supporting Task-Stage Knowledge: A Hierarchical Clustering Technique , 2006, PAKM.

[26]  Wolfgang Nejdl,et al.  Evaluating Personal Information Management Using an Activity Logs Enriched Desktop Dataset , 2008 .

[27]  Tessa A. Lau,et al.  Sheepdog: learning procedures for technical support , 2004, IUI '04.

[28]  Thomas G. Dietterich,et al.  Discovering frequent work procedures from resource connections , 2009, IUI.

[29]  Nuria Oliver,et al.  SWISH: semantic analysis of window titles and switching history , 2006, IUI '06.

[30]  Marko Robnik-Sikonja,et al.  An adaptation of Relief for attribute estimation in regression , 1997, ICML.

[31]  Xufeng He,et al.  Switch detector: an activity spotting system for desktop , 2011, CIKM '11.

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

[33]  Hiroshi Motoda,et al.  Computational Methods of Feature Selection , 2022 .

[34]  Víctor M. González,et al.  No task left behind?: examining the nature of fragmented work , 2005, CHI.

[35]  Mark Dredze,et al.  Automatically classifying emails into activities , 2006, IUI '06.

[36]  Oliver Brdiczka,et al.  Identifying Routine and Telltale Activity Patterns in Knowledge Work , 2011, 2011 IEEE Fifth International Conference on Semantic Computing.

[37]  Matthai Philipose,et al.  The Probabilistic Activity Toolkit: Towards Enabling Activity-Aware Computer Interfaces , 2003 .