A 'Smart' Email Software Organizes Your Tasks

You probably receive dozens of emails every day about various aspects of your business or personal life. And because your email program doesn't understand the relationship between messages, except for the occasional thread, you have to manage your activities by looking through lists of emails. But now, two computer scientists from University College Dublin (UCD) and IBM have developed the Active Email Manager (AEM) and have even filed patents for a 'smart' email program. Their prototype can make the difference between work-related tasks -- and assign them to a workflow -- and personal email. This software could be integrated in commercial products from IBM within two years. Read more...

Here are some details about the project.
A University College Dublin (UCD) scientist has filed a patent application for a new technology that he believes can turn email into a much more effective business tool. US-born Dr Nicholas Kushmerick, a senior lecturer in the Department of Computer Science at UCD, has developed the technology over the past year during his part-time position as visiting scientist on IBM’s Centre for Advanced Studies (CAS) initiative.
Kushmerick developed the technology, known as Active Email Manager (AEM), in concert with New York-based IBM researcher Tessa Lau. Together they developed a machine-learning algorithm that automatically keeps track of tasks and associated emails, in order to build up a work flow for each task.
"The vision is that rather than come in and download all your emails, you could just call up your to do list and manage your activities," Kushmerick explains.

Now, the two researchers have developed a prototype of the software and are busy testing it. And IBM wants to use the technology in some of its future products.
The technology is currently being appraised by two separate research groups within IBM, with the aim of turning into a commercial product. One of these is the Massachusetts-based product development team that develops IBM’s suite of collaboration software, Lotus Workplace. "There are some pretty intensive discussions going on now to see if we can get enough attention and convince them that our idea is feasible and that they would put it into their product pipeline," says Kushmerick.

The research work has been presented at the 2005 International Conference on Intelligent User Interfaces (IUI 2005) which has been held on January 9-12, 2005, in San Diego, California. You can find the abstract of the paper called "Automated Email Activity Management: An Unsupervised Learning Approach" in the 2005 Conference Program.
Many structured activities are managed by email. For instance, a consumer purchasing an item from an e-commerce vendor may receive a message confirming the order, a warning of a delay, and then a shipment notification. Existing email clients do not understand this structure, forcing users to manage their activities by sifting through lists of messages. As a first step to developing email applications that provide high-level support for structured activities, we consider the problem of automatically learning an activity's structure. We formalize activities as finite-state automata, where states correspond to the status of the process, and transitions represent messages sent between participants. We propose several unsupervised machine learning algorithms in this context, and evaluate them on a collection of e-commerce email.

Please note that this work received a Honorable Mention for Outstanding Paper Award at IUI 2005.

For more information, here is a link to the full version of this paper (PDF format, 8 pages, 234 KB), available from Kushmerick's website