edit iems

iems Eric McCreath, ericm@cs.anu.edu.au, Elizabeth Crawford, ehc@cs.cmu.edu, Judy Kay, judy@it.usyd.edu.au School of Information Technologies, University of Sydney Contact Person Judy Kay judy@it.usyd.edu.au Project Description People currently receive large amounts of email. There is considerable evidence that some of us are overwhelmed by this load, at times. For example, there are people who never seem to answer my email in a timely manner - not doubt, not you :-). The goal of this work is to help people deal with the problem, not just as it stands, but as it will evolve. Part of the challenge is that people use email and associated mail management interfaces for a range of tasks: organising their workload, keeping reminders and records, managing projects ..... Although we might well be able to build elegant applications for some of these tasks, there is a real problem in getting people to use them. The current reality is that asyncronous communication via email is a multi-faceted and important communication mechanism. There are many elements to the solution. Our current vision is to learn how to build systems that can help people organise email more effectively, perhaps to have some of it handled automatically. At the same time, we want the user to be in control of the processes and able to scrutinise the system to work out just what information the system holds and how it is used. This project has provided foundations on two fronts. First, it has explored a novel interface, reported in the IUI paper below. This organises the inbox into predicted categories. The second part of this work has been the exploration of different machine learning algorithms for the task of predicting the way that the user will classify their email.

Our contributions include:

• A novel interface for viewing a person's inbox with mail automatically organised into the predicted user categorisation, described in the 2002 IUI paper.
• A novel learning algorithm that combines instance based and rule based information, which is described in our ICML 2002 paper.
• Design of a testing framework for e-mail classification that takes into account the temporal nature of the data. This frame-work is described in our UM 2001 workshop paper and the further developed work in the ADCS 2001 paper.
• Design of an e-mail interface aimed at making classification decisions scrutable, and minimizing the cost of incorrect classification to the user. For further information please see our IUI 2002 paper.
• Exploration of the consistency of human classification over a long period and how this defines a limit on the potential accuracy of machine classifiers, described in the 2003 UM paper.
• Exploration of the broader social context, in the 2001 CRF paper.
• Extension of the approach to communities, in the ADCS 2003 paper.
• Empirical evaluation of a variety of Machine Learning techniques on a per-user and per-folder basis, described in the 2006 AJIIPS paper.

Acknowledgements: This work was funded by a University of Sydney Sesquicentenary Grant, 2001, McCreath and Kay. It has also received support from the SITCRC, Smart Internet Technology CRC.

Key Publications

E. McCreath, J. Kay, and E. Crawford. IEMS - an approach that combines hand-crafted rules with learnt instance-based rules. Australian Journal of Intelligent Information Processing Systems, 9(1):49-63, 2006. [View Details]

E. McCreath and J. Kay. Limitation of performance measures. In P. Brusilovsky, A. Corbett, and F. de Rosis, editors, Proceedings of User Modelling 2003, Lecture notes in Artificial Intelligence (LNAI/LNCS), pages 263-272. Springer-Verlag, 2003. [View Details]

E. McCreath and J. Kay. Iems: Helping users manage email. In P. Brusilovsky, A. Corbett, and F. de Rosis, editors, Proceedings of UM 2003, 9th International Conference on User Modeling, volume 2703 of Lecture Notes in Computer Science, pages 263-272. Springer-Verlag (Berlin, Heidelberg), 2003. [View Details]

F. Verhein, J. Kay, I. Koprinska, and E. McCreath. Classifying public announcements for user communities. In P. Bruza and J. Thom, editors, Proceedings of ADCS 2003, 8th Australasian Document Computing Symposium, pages 15-24. ADCS, 2003. [View Details]

E. Crawford, J. Kay, and E. McCreath. Iems - the intelligent email sorter. In C. Sammut and A. G. Hoffmann, editors, Proceedings of ICML 2002, International Conference on Machine Learning, pages 83-90. Morgan Kaufmann (San Francisco, CA, USA), 2002. [View Details]

E. Crawford, J. Kay, and E. McCreath. An intelligent interface for sorting electronic mail. In Proceedings of IUI 2002, Intelligent User Interfaces, pages 182-183. ACM Press (New York, NY, USA), 2002. [View Details]

E. Crawford, J. Kay, and E. McCreath. Automatic induction of rules for e-mail classification. In A. M. Vercoustre and J. Kay, editors, ADCS'2001, Australian Document Computing Symposium (Proceedings), pages 13-20, 2001. [View Details]

J. Kay and E. McCreath. Automatic induction of rules for e-mail classification (workshop on machine learning for user modelling). In Workshop on Machine Learning for User Modelling UM2001 (Proceedings), pages 59 - 66, 2001. [View Details]

S. Singh, J. Kay, A. Ryan, E. McCreath, and B. Kummerfeld. Managing corporate email: connecting the social, policy and technical perspectives. In Communications Research Forum, 2001. [View Details]