Which algorithm is commonly used for email spam filtering?
Naive Bayes classifier
Explanation:
The Naive Bayes classifier is commonly used for email spam filtering because it can efficiently classify emails by analyzing the probability of words and patterns appearing in spam or non-spam messages.
Example:
- Words like “free,” “offer,” or “win” may increase the probability that an email is spam.
- The model learns from previous labeled emails and predicts whether new emails are spam or legitimate.
Why not the others?
- a) K-means clustering → Used for grouping similar data without labels (unsupervised learning).
- b) Logistic regression → Can be used for classification but is less traditionally associated with spam filtering.
- d) Decision tree → Can classify data but is not the most common choice for basic spam filtering.
