Intelligent email: Aiding users with AI

2008

Abstract 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.

2009

ABSTRACT RADAR is a large multi-agent system with a mixedinitiative user interface designed to help office workers cope with email overload. RADAR agents observe experts performing tasks and then assist other users who are performing similar tasks. The Email Classifier learns to identify tasks contained within emails and then inspects new emails for similar tasks, which are presented in a novel task-management user interface.

IEEE/WIC International Conference on Intelligent Agent Technology, 2003. IAT 2003., 2003

In this paper, we describe EMMA (E-Mail Management Assistant), an e-mail system that addresses the process of e-mail management, from initially sorting messages into virtual folders, to prioritizing, reading, replying (automatically or semi-automatically), archiving and deleting mail items. EMMA attains a high degree of accuracy on email classification by using a rule-based approach known as Ripple Down Rules (RDR) as the basis of rule construction. In contrast to traditional rule-based systems, RDR systems provide extensive help to the user in defining rules and maintaining the consistency of a rule base, making EMMA easy to use. We discuss the results of evaluating the usability of EMMA on a trial of independent users.

2009 IEEE Conference on Commerce and Enterprise Computing, CEC 2009, 2009

According to recent surveys, information workers send and receive an average of 133 messages per day 1 , and users talk about "living" in email, spending an average of 21 percent of their time on it, as well as reporting general problems with overload. Information created by a business can represent either an asset or a liability, depending largely on how well it is managed. Email is no different in this respect: it can be a highly efficient and useful tool for communication, but only if the information it contains can be managed effectively. One of the main drawbacks of email usage today is its insufficient integration into the collective workspace environment. We believe that by integrating it with other external information (both on the desktop and on distributed servers), one can migrate some of this information to more appropriate storage environments, thereby partly addressing the problem of overload and offering users an integrated access to data and functionality. Currently, there is much research in the area of both personalised and business information management, but very little research that focuses on email as the primary information source, despite its ubiquity. In this paper we survey the current state of the art in email processing and communication research, focusing on the current and potential roles played by email in information management, and commercial and research efforts to integrate a semantic-based approach to email. Keywords-email research; state of the art; intelligent email 9

2010

Abstract RADAR is a multiagent system with a mixed-initiative user interface designed to help office workers cope with email overload. RADAR agents observe experts to learn models of their strategies and then use the models to assist other people who are working on similar tasks. The agents' assistance helps a person to transition from the normal email-centric workflow to a more efficient task-centric workflow. The Email Classifier learns to identify tasks contained within emails and then inspects new emails for similar tasks.

2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, 2008

EMMA is an e-mail management assistant based on Ripple Down Rules, providing a high degree of classification accuracy while simplifying the task of maintaining the consistency of the rule base. A Naive Bayes algorithm is used to improve the usability of EMMA by suggesting keywords to help the user define rules. In this paper, we report on an experimental evaluation of EMMA on 16 998 pre-classified messages. The aim of the evaluation was to show that the Ripple Down Rule technique used in EMMA applies to large-scale data sets in realistic organizational contexts. The results showed conclusively that EMMA attained the agreed success criteria for the evaluation and that the knowledge acquisition method used in EMMA outperforms standard machine learning methods.

2002

A key element of the CoolAgent Personal Assistant vision is the active management and use of personal, team and organizational information. The finding, filtering, composing, routing and information-triggered notification to a (mobile) user, adapted to the location, schedule, available appliances, tasks and other personal and team context is a key capability within the vision of an agent-based system for personal, professional and team activities. In this paper we report on the current status of a key element, the personal email assistant (PEA), which provides a customizable, machinelearning-based environment to support the activities of a major time sink of our daily lives-the processing of email. The system has been designed to be usable either with or without an agent-based infrastructure, and to be useful with a variety of email systems. In its current form, it leverages and augments the capabilities provided by Exchange and Outlook. It provides capabilities of: smart vacation responder, junk mail filter, efficient email indexing and searching, deleting, forwarding, re-filing, and prioritizing of email. A key contribution of our work has been to leverage high-quality open source components for information retrieval, machine learning, agents and rules to provide a powerful, flexible and robust capability.

The stress resulting from the daily demands of email exchange and management has been labelled email overload [4, 13]. The extent to which individuals are affected by email overload has much to do with personal, cultural, and contextual differences. However, in general people are inefficient at dealing with email and could potentially reduce the stress associated with it if they changed their behaviour. In this paper, we review some of the strategies offered in the literature, as well as some email tools that have been developed to help people manage their inboxes. We point out the benefits and disadvantages of them, suggesting that adaptive approaches might be more effective at facilitating email behaviour changes than fixed one-size-fits-all solutions. We argue that the adaptation should be the result of personalisation (controlled by the system) and customisation (controlled by the user) because these processes support behaviour change in different ways.

2022 International Conference on Decision Aid Sciences and Applications (DASA)

In this paper, a workflow for designing a bot using Robotic Process Automation (RPA), associated with Artificial Intelligence (AI) that is used for information extraction, classification, etc., is proposed. The bot is equipped with many features that make email handling a stress-free job. It automatically login into the mailbox through secured channels, distinguishes between the useful and not useful emails, classifies the emails into different labels, downloads the attached files, creates different directories, and stores the downloaded files into relevant directories. It moves the not useful emails into the trash. Further, the bot can also be trained to rename the attached files with the names of the sender/applicant in case of a job application for the sake of convenience. The bot is designed and tested using the UiPath tool to improve the performance of the system. The paper also discusses the further possible functionalities that can be added on to the bot.

1996

Email is one oftl~ most successful computer applicmiom yet devised. Our empin~:al ct~ta show however, that althongh email was origiraUy designed as a c~nmunica/ons application, it is now used for ~tional funaions, that it was not designed for, such as tab management and persona/ afoOt/v/rig. We call this ernt~l oveHoad We demonstrate that email overload creates problems for personal information manageaa,cnt: users eden have cluttered inboxes cor~mining hundreds of n~:age~¢, incl~rling outstanding tasks, partially read documents and conversational threads. Furthermore,, user attemt:Xs to rationalise their inbox~ by ~ing are ~Ron unsuccessful, with the consequence that important rr~ges get overlooked, or "lost" in archives. We explain how em~l over/oad/ng arises and propose technical solutions to the problem.