With the growth in the communication over Internet via short messages, messaging services and chat, still emails are the most preferred communication method. Thousands of emails are been communicated everyday over different service providers. The emails being the most effective communication methods can also attract a lot of spam or irrelevant information. The spam emails are annoying and consumes a lot of time for filtering. Regardless to mention, the spam emails also consumes the main allocated inbox space and at the same time causes huge network traffic. The filtration methods are miles away from perfection as most of these filters depends on the standard rules, thus making the valid emails marked as spam. The first step of any email filtration should be extracting the key phrases from the emails and based on the key phrases or mostly used phrases the filters should be activated. A number of parallel researches have demonstrated the key phrase extraction policies. Nonetheless, the methods are truly focused on domain specific corpuses and have not addressed the email corpuses. Thus this work demonstrates the key phrases extraction process specifically for the email corpuses. The extracted key phrases demonstrate the frequency of the words used in that email. This analysis can make the further analysis easier in terms of sentiment analysis or spam detection. Also, this analysis can cater to the need for text summarization. The proposed component based framework demonstrates a nearly 95% accuracy.

The classification of emails is one crucial part of the email filtering process, as emails have become one of the key methods of communication. The process for identifying safe or unsafe emails is complex due to the diversified use of the language. Nonetheless, most of the parallel research outcomes have demonstrated significant benchmarks in identifying email spam. However, the standard processes can only identify the emails as spam or ham. Henceforth, a detailed classification of the emails has not been achieved. Thus, this work proposes a novel method for the identification of the emails into various classes using the proposed deep clustering process with the help of the ranking of words into severity. The proposed work demonstrates nearly 99.4% accuracy in detecting and classifying the emails into a total of five classes.