Personal Information Organization using Web Annotations

Abstract

As more information is made available online, users collect information in
personal information spaces like bookmarks and emails. While most users feel that
organizing these collections is crucial to improve access, studies have shown that this
activity is time consuming and highly cognitive. Automatic classification has been used
but by relying on the full text of the documents, they do not generate personalized
classifications. Our approach is to give users the ability to annotate their documents as
they first access them. This annotation tool is unobtrusive and welcome by most users
who generally miss this facility when dealing with digital documents. Our experiments
show that these annotations can be used to generate personalized classifications of
annotated Web pages.