Detecting Spam Emails

Electronic mail is a ubiquitous internet service for exchanging messages between people. A typical problem in this sphere of communication is identifying and blocking unsolicited and unwanted messages. Spam detectors undertake part of this role; ideally, they should not let spam escape uncaught while not obstructing any non-spam.

This chapter deals with this problem from a machine learning (ML) perspective and unfolds as a series of steps for developing and evaluating a typical spam detector. First, we elaborate on the limitations of performing spam detection using traditional programming. Next, we introduce the basic techniques for text representation and preprocessing. Finally, we implement two classifiers using an open source dataset and evaluate their performance based on standard metrics.

By the end of the chapter, you will be able to understand the nuts and bolts behind the different techniques and implement them in Python. But, more importantly, you should be capable of seamlessly applying the same pipeline to similar problems.

We go through the following topics:

• Obtaining the data
• Understanding its content
• Preparing the datasets for analysis
• Training classification models
• Realizing the tradeoffs of the algorithms
• Assessing the performance of the models