SMS (Short Message Service) is a popular and quick service for the communication. The problem occurs when the user does not want to receive a particular text or text from particular type of IDS i.e. is called spam. To prevent such kind of message, text classification methods have been proposed. Most of the current methods of spam detection involve using keyword filters to separate spam and regular messages. This paper focuses on the text classification methods like tree architecture, ICA algorithm and Neural Network algorithm for the text classification to prevent the user from unwanted spam messages.