An Ontology-Based Approach for Detecting Knowledge Intensive Tasks

In the context detection field, an important challenge is automatically detecting the user’s task, for providing contextualized and personalized user support. Several approaches have been proposed to perform task classification, all advocating the window title as the best discriminative feature. In this paper we present a new ontology-based task detection approach, and evaluate it against previous work. We show that knowledge intensive tasks cannot be accurately classified using only the window title. We argue that our approach allows classifying such tasks better, by providing feature combinations that can adapt to the domain and the degree of freedom in task execution.

[1]  Matthias Baldauf,et al.  A survey on context-aware systems , 2007, Int. J. Ad Hoc Ubiquitous Comput..

[2]  Guus Schreiber,et al.  Knowledge Engineering and Management: The CommonKADS Methodology , 1999 .

[3]  Akrivi Katifori,et al.  Task-Centered Information Management , 2007 .

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

[5]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[6]  Ansgar Bernardi,et al.  Overview and Outlook on the Semantic Desktop , 2005, Semantic Desktop Workshop.

[7]  Predrag V. Klasnja,et al.  The personal project planner: planning to organize personal information , 2008, CHI.

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

[9]  Roman Kern,et al.  Knowledge Discovery using the Knowminer Framework , 2009 .

[10]  Siegfried Handschuh,et al.  The NEPOMUK Project - On the way to the Social Semantic Desktop , 2007 .

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

[12]  Andreas S. Rath,et al.  Context-Aware Knowledge Services , 2008 .

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

[14]  James Allan,et al.  Meeting of the MINDS: an information retrieval research agenda , 2007, SIGF.

[15]  Wil M. P. van der Aalst,et al.  Process mining: a research agenda , 2004, Comput. Ind..

[16]  David Garlan,et al.  Context is key , 2005, CACM.

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

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

[19]  Ian Witten,et al.  Data Mining , 2000 .

[20]  Andreas Schmidt,et al.  Bridging the Gap between Knowledge Management and E-Learning with Context-Aware Corporate Learning , 2005, Wissensmanagement.

[21]  Saul Greenberg,et al.  Context as a Dynamic Construct , 2001, Hum. Comput. Interact..

[22]  Andreas S. Rath,et al.  KnowSe: Fostering user interaction context awareness , 2009 .

[23]  Erik Duval,et al.  Tracking Actual Usage: the Attention Metadata Approach , 2007, J. Educ. Technol. Soc..

[24]  Akrivi Katifori,et al.  Task-Centred Information Management , 2007, DELOS.

[25]  John C. Tang,et al.  Recent shortcuts: using recent interactions to support shared activities , 2007, CHI.

[26]  Clemens H. Cap,et al.  Paving the Path to Automatic User Task Identification , 2008, CSKGOI.

[27]  Thomas G. Dietterich,et al.  Detecting and correcting user activity switches: algorithms and interfaces , 2009, IUI.

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

[29]  Andreas S. Rath,et al.  Contextualized knowledge services for personalized learner support , 2009 .

[30]  Claudia Linnhoff-Popien,et al.  A Context Modeling Survey , 2004 .

[31]  Michael S. Bernstein,et al.  Gui --- phooey!: the case for text input , 2007, UIST.

[32]  Gregory D. Abowd,et al.  A Conceptual Framework and a Toolkit for Supporting the Rapid Prototyping of Context-Aware Applications , 2001, Hum. Comput. Interact..