Email task management: An iterative relational learning approach

  • Khoussainov R
  • Kushmerick N
  • 18

    Readers

    Mendeley users who have this article in their library.
  • 26

    Citations

    Citations of this article.

Abstract

Today’s email clients were designed for yes-
terday’s email. Originally, email was merely
a communication medium. Today, people en-
gage in a variety of complex behaviours using
email, such as project management, collabora-
tion, meeting scheduling, to-do tracking, etc.
Our goal is to develop automated techniques to
help people manage complex activities or tasks in
email. The central challenge is that most activi-
ties are distributed over multiple messages, yet
email clients allow users to manipulate just iso-
lated messages. We describe machine learning
approaches to identifying tasks and relations be-
tween individual messages in a task (i.e., find-
ing cause-response links between emails) and for
semantic message analysis (i.e., extracting meta-
data about how messages within a task relate
to the task progress). Our key innovation com-
pared to related work is that we exploit the rela-
tional structure of these two problems. Instead
of attacking them separately, in our synergis-
tic iterative approach, relations identification is
used to assist semantic analysis, and vice versa.
Our experiments with real-world email corpora
demonstrate an improvement compared to non-
relational benchmarks

Author-supplied keywords

  • 2005
  • agile_processes
  • email
  • task_management
  • workflow

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

  • SCOPUS: 2-s2.0-84873891599
  • PUI: 373614090
  • SGR: 84873891599

Authors

  • R Khoussainov

  • N Kushmerick

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free