Machine Learning

How to Develop a Multichannel CNN Model for Text Classification

Last Updated on September 3, 2020

A standard deep learning model for text classification and sentiment analysis uses a word embedding layer and one-dimensional convolutional neural network.

The model can be expanded by using multiple parallel convolutional neural networks that read the source document using different kernel sizes. This, in effect, creates a multichannel convolutional neural network for text that reads text with different n-gram sizes (groups of words).

In this tutorial, you will discover how to develop a multichannel convolutional neural network for sentiment prediction on text movie review data.

After completing this tutorial, you will know:

  • How to prepare movie review text data for modeling.
  • How to develop a multichannel convolutional neural network for text in Keras.
  • How to evaluate a fit model on unseen movie review data.

Kick-start your project with my new book Deep Learning for Natural Language Processing, including step-by-step tutorials and the Python source code files for all examples.

Let’s get started.

  • Update Feb/2018: Small code change to reflect changes in Keras 2.1.3 API.
  • Update Aug/2020: Updated link to movie review dataset.
How to Develop an N-gram Multichannel Convolutional <a href=To finish reading, please visit source site