An integrated framework for solving email management problems with unsupervised machine learning techniques and artificial neural networks

Abstract

The volume of email being received by email users nowadays is enormous. Email
users spend significant amount of time to manage their emails, which tends to be tedious. The task of grouping emails for further processing often discourages users from filing their mail, resulting in unmanageable mailboxes that contain hundreds or even thousands of unsorted messages. The present work starts by redeveloping a systematic framework of email management. Major email managing tasks were identified, investigated and classified into categories, namely, email summarisation, email grouping and email urgency reply prediction, the details of which are provided within this research work. Any possible solution to problems of managing emails, such as email overloads and email congestions should eliminate the need for human intuition in email management systems. Hence this work focuses on utilising unsupervised machine learning techniques in the development of key email management tools such as adaptive mail summa riser, which provide precise summaries of email messages, a mail cluster, which groups email messages based on the focus of the mail and a mail predictor, which determines mails that need attention or require urgent replies.
This work was carried out in different stages. First, an unsupervised mail summariser learner was proposed and developed, that utilises knowledge, as well as words and phrases modelling (keywords extractions) approach to provide a coherent email summaries. Secondly, the task of grouping emails into categories based on the focus of the mail contents is explored. Email evolving clustering method was developed to organise mails into relevant and accurate clusters, resulting in a clustering similarity matrix. Artificial neural networks with back propagation techniques were involved. Thirdly, a reply prediction technique was proposed for the purpose of classifying mail into different reply urgency index by exploiting the unsupervised learning with human justifications in the early phase. The research work eventually integrates all three into an email management system. An email management toolkit was then developed to test, evaluate and illustrate the proposed email management system. The prototype toolkit can be organised as a plug-in for most of email clients. A largescale case study was conducted in which the effectiveness of the systematic email management framework developed in this work was demonstrated.

Date of Award	Apr 2010
Original language	English
Awarding Institution	University of Portsmouth
Supervisor	Shikun Zhou (Supervisor), David Sanders (Supervisor) & Rinat Khusainov (Supervisor)