CENSORSHIP AGENT: IDENTIFYING AND DETERMINING OFFENSIVE WORDS

The advancement in computing enables anyone to become information producer,
resulting in rapidly growing information in the Internet. One concern that arises from
this phenomenon is the easy access to offensive, vulgar and/or obscene page by
anyone with access to the Internet. The solution for this concern is filtering software.
Current existing filtering software required human intervention in determining the
harmfulness of page content. The fear of this trend brings out the desire to protect a
community, especially children from the harmful content available. This paper
represents a prototype of application that performs the task of identifying and
determining the harmfulness content of a document without human intervention. The
prototype is designed to extract the content of the document, stem the words into its
root, and compare each word to the list of harmful words.