| Summary: | 碩士 === 國立臺灣大學 === 資訊工程學系 === 86 === A personalized information filtering system must specialize to
current interests of the user and adapt as the change over time.
This thesis presents an E-mail agent as a personalized filtering
system.
An approach to classify mails according to user''s interests
or habits and one to prioritize user''s new mails are proposed.
This thesis presents the basic framework for personalized E-mail
agents, and describes an implementation P@rty. The classification
mechanisms used are the vector space model and the feature
selection. The prioritization mechanisms used are relevance
feedback and time decay. The user interface is friendly.
Experimental results indicate that P@rty can be personalized
to serve some of the mails filtering needs of the user, in particular,
those that are more regular and predictable. Relevance feedback
is good for specializing to user interests.
|
|---|
