University of Houston
Department of Computer Science

In partial fulfillment of the Requirements for the Degree of
Master of Science


Ashit Mohanlal

will defend his/her thesis

Collaborative Filtering as an Effective Tool against
Unsolicited Commercial Emails


Abstract

Unsolicited Commercial Mails (UCE), better known as Spam Mails, have become a big problem for Internet users. Once a user is registered for an online account, game, or newsletter it does not take much time until the first unsolicited Mails find their way into the user’s mailbox. To avoid wastage of hours of users’ time and efforts spent in deleting and sorting their mails, several technique and forms of filtering have emerged over the time. These filter programs help the user by sorting out unsolicited emails automatically. However, it is much easier for a human being to identify an email as being spam, faster and more accurately than any software program can. This is mainly because a software program has to do several rounds of checks and comparisons using a pre-defined set of rules before it can come to a definitive conclusion. It works on the knowledge / information fed in by humans. In spite of this, the filtering done may not be sufficient. A filtering program is limited by the fact that it relies on a pre-defined set of rules with some heuristics. Spammers are extremely quick at adapting their techniques so as to circumvent the very rules that a filtering program relies on. As an alternative to purely rule based filtering and a complement to the existing anti-spam technologies, we propose a collaborative method of filtering spam where users in the system collaborate to identify spam and effectively benefit the rest of the users in the system.

Date: Wednesday, November 17, 2004
Time: 9:15 AM
Place: 550-PGH


Faculty, students, and the general public are invited.
Thesis Advisor: Dr. Ernst L. Leiss