Cluster Mail: Difference between revisions
From Computer Laboratory Group Design Projects
Jump to navigationJump to search
(Created page with "Andy Ide <asi@netcraft.com> Everybody has a different approach to categorising email, but nobody has time to do it properly. Your task is to create a new kind of email client...") |
No edit summary |
||
| (One intermediate revision by the same user not shown) | |||
| Line 1: | Line 1: | ||
Based on conversation with a potential client who has asked for their details to be removed from the wiki. | |||
Everybody has a different approach to categorising email, but nobody has time to do it properly. Your task is to create a new kind of email client that uses unsupervised machine learning techniques to infer topic clusters from content. The user interface should allow users to deal with various personalised clusters in different ways according to their mood and level of concentration at the time. Use the IMAP protocol to automatically file clustered messages on the server, or (if feeling brave) automatically reply to them. A useful side effect of this mail client will be that spam and phishing mail gets the priority it deserves. | Everybody has a different approach to categorising email, but nobody has time to do it properly. Your task is to create a new kind of email client that uses unsupervised machine learning techniques to infer topic clusters from content. The user interface should allow users to deal with various personalised clusters in different ways according to their mood and level of concentration at the time. Use the IMAP protocol to automatically file clustered messages on the server, or (if feeling brave) automatically reply to them. A useful side effect of this mail client will be that spam and phishing mail gets the priority it deserves. | ||
Latest revision as of 11:10, 6 July 2022
Based on conversation with a potential client who has asked for their details to be removed from the wiki.
Everybody has a different approach to categorising email, but nobody has time to do it properly. Your task is to create a new kind of email client that uses unsupervised machine learning techniques to infer topic clusters from content. The user interface should allow users to deal with various personalised clusters in different ways according to their mood and level of concentration at the time. Use the IMAP protocol to automatically file clustered messages on the server, or (if feeling brave) automatically reply to them. A useful side effect of this mail client will be that spam and phishing mail gets the priority it deserves.
