RADAR: A Personal Assistant that Learns to Reduce Email Overload

Email client software is widely used for personal task management, a purpose for which it was not designed and is poorly suited. Past attempts to remedy the problem have focused on adding task management features to the client UI. RADAR uses an alternative approach modeled on a trusted human assistant who reads mail, identifies task-relevant message content, and helps manage and execute tasks. This paper describes the integration of diverse AI technologies and presents results from human evaluation studies comparing RADAR user performance to unaided COTS tool users and users partnered with a human assistant. As machine learning plays a central role in many system components, we also compare versions of RADAR with and without learning. Our tests show a clear advantage for learning-enabled RADAR over all other test conditions.

[1]  Rebecca E. Grinter,et al.  Quality versus quantity: e-mail-centric task management and its relation with overload , 2005 .

[2]  Carrie Gates,et al.  We have met the enemy and he is us , 2009, NSPW '08.

[3]  Candace L. Sidner,et al.  Email overload: exploring personal information management of email , 1996, CHI.

[4]  Stephen F. Smith,et al.  Learning User Preferences in Distributed Calendar Scheduling , 2004, PATAT.

[5]  Aaron Steinfeld,et al.  Evaluation of an integrated multi-task machine learning system with humans in the loop , 2007 .

[6]  Alexander I. Rudnicky,et al.  A Briefing Tool that Learns Individual Report-Writing Behavior , 2006, 2006 18th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'06).

[7]  Robert E. Kraut,et al.  Email overload at work: an analysis of factors associated with email strain , 2006, IEEE Engineering Management Review.

[8]  Wendy E. Mackay,et al.  More than just a communication system: diversity in the use of electronic mail , 1988, CSCW '88.

[9]  Neil Yorke-Smith,et al.  Uncertainty in Soft Temporal Constraint Problems:A General Framework and Controllability Algorithms forThe Fuzzy Case , 2006, J. Artif. Intell. Res..

[10]  Stephen F. Smith,et al.  Scheduling with Uncertain Resources: Search for a Near-Optimal Solution , 2006, 2006 IEEE International Conference on Systems, Man and Cybernetics.

[11]  Eric Horvitz,et al.  Disruption and recovery of computing tasks: field study, analysis, and directions , 2007, CHI.

[12]  Stephen F. Smith,et al.  Advising busy users on how to cut corners , 2008 .

[13]  Zzzzzz Zzzzzzz.  Learning To Understand Web Site Update Requests , 2004 .

[14]  John Zimmerman,et al.  Survey measures for evaluation of cognitive assistants , 2007 .

[15]  John Zimmerman,et al.  Learning information intent via observation , 2007, WWW '07.

[16]  Yiming Yang,et al.  Robustness of adaptive filtering methods in a cross-benchmark evaluation , 2005, SIGIR '05.

[17]  John Zimmerman,et al.  Vio: a mixed-initiative approach to learning and automating procedural update tasks , 2007, CHI.

[18]  Eugene Fink,et al.  Scheduling with Uncertain Resources Part 3: Elicitation of Additional Data , 2006 .

[19]  Liangxiao Jiang,et al.  Hidden Naive Bayes , 2005, AAAI.

[20]  Steven L. Rohall,et al.  Email Visualizations to Aid Communications , 2001 .

[21]  Olle Bälter,et al.  Electronic mail in a working context , 1998 .

[22]  Kenrick J. Mock.  An experimental framework for email categorization and management , 2001, SIGIR '01.

[23]  Mike Song,et al.  The Hamster Revolution: How to Manage Your Email Before It Manages You , 2007 .

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

[25]  William W. Cohen,et al.  Improving “Email Speech Acts” Analysis via N-gram Selection , 2006, HLT-NAACL 2006.

[26]  Donna Gates,et al.  From Language to Time: A Temporal Expression Anchorer , 2006, Thirteenth International Symposium on Temporal Representation and Reasoning (TIME'06).

[27]  Eugene Fink,et al.  Scheduling with Uncertain Resources: Representation and Utility Function , 2006, 2006 IEEE International Conference on Systems, Man and Cybernetics.

[28]  Anoop Gupta,et al.  Supporting Email Workflow , 2001 .

[29]  Jaime G. Carbonell,et al.  Paired Sampling in Density-Sensitive Active Learning , 2008, ISAIM.