From the course: Natural Language Processing for Speech and Text: From Beginner to Advanced

Unlock the full course today

Join today to access over 24,700 courses taught by industry experts.

Statistical: Naive Bayes classifiers

Statistical: Naive Bayes classifiers - Python Tutorial

From the course: Natural Language Processing for Speech and Text: From Beginner to Advanced

Start my 1-month free trial Buy for my team

Statistical: Naive Bayes classifiers

“

- [Instructor] Naive Bayes Classifiers are a group of probabilistic, supervised learning algorithms based on Bayes theorem for classification task. Bayes' theorem describes the probability of an event based on prior knowledge of conditions related to the event. It's described as naive because in real scenarios, features used in classification are often not conditionally independent of each other. In the training phase, the prior class probability, future likelihood are calculated using the Bayes theorem. And then the prediction phase, where the probability of a new data point belong to a class, is calculated. The data point is estimated to belong to the highest posterior probability. In NLP, they're commonly used for text classification, document categorization, named entity recognition, and recommendation systems.

Contents