Spam Sieve for Emails

Repo: github.com

  • Tech Stack: Python, NLTK, Pandas, Scikit-learn, TextBlob

Spam classification system to classify emails as "spam" or "ham" (non-spam) using both the Naive Bayes and Decision Trees algorithms in Python.

Achieved an accuracy of 65.4% for the Naive Bayes model and 70.83% for the Decision Tree model.

Key Features

  • Built a spam classification system to classify emails as "spam" or "ham" (non-spam) using both the Naive Bayes and Decision Trees algorithms.
  • Achieved an accuracy of 65.4% for the Naive Bayes model.
  • Achieved an accuracy of 70.83% for the Decision Tree model.
  • Implemented preprocessing techniques to clean and normalize the text data.
  • Utilized NLTK and TextBlob for natural language processing and sentiment analysis.