1. Spam Detection

Duration2h30 x 2 AI Banned

Introduction

This practical session introduces fundamental concepts of Natural Language Processing (NLP) through a hands-on spam detection workshop. You’ll learn to process text data, extract meaningful features, and build machine learning models that can distinguish between spam and legitimate messages across different communication channels.

Through this guided notebook experience, you will master essential NLP skills:

  • Text Preprocessing: Learn tokenization strategies, case normalization, and stop word handling for optimal feature extraction
  • Feature Engineering: Transform unstructured text into numerical representations using bag-of-words and frequency-based approaches
  • Cross-Domain Analysis: Understand how models perform across different text domains (SMS vs email) and communication contexts
  • Model Evaluation: Apply precision, recall, and accuracy metrics specifically relevant to text classification tasks
  • Domain Transfer: Explore the challenges of applying models trained on one text type to another, a common real-world scenario

This session uses authentic SMS and email datasets to provide realistic experience with text classification challenges. You’ll discover how linguistic differences between communication channels affect model performance and learn strategies for robust text classification systems.

Getting Started

You have access to a JupyterHub environment that already contains all the necessary data, notebooks, and required Python libraries. Simply access the environment and start working immediately!

Access JupyterHub

Local Installation

If you prefer to work locally, please refer to the activity Setup your first Data Science project first to ensure you have all the necessary Python packages installed.

You can download the notebook and the data for this practical session using the links below:

Download Notebook (Right-click → Save as…)

Download data