Text classification using Convolutional Neural Networks (CNNs) is a popular deep learning technique for natural language processing (NLP) tasks. CNNs use filters to extract features from the text, and then use these features to classify the text into predefined categories.

The input data for CNNs in text classification is typically represented as a sequence of word embeddings, which are learned representations of words in a high-dimensional space. The convolutional layer in the CNN applies filters to the word embeddings, which allows the network to identify important features in the text.

After the convolutional layer, the output is typically fed through a pooling layer to further reduce the dimensionality of the features. The pooled features are then fed into one or more fully connected layers, which perform the classification.

Text classification using CNNs has achieved state-of-the-art results on various benchmark datasets, such as sentiment analysis, topic classification, and text categorization. However, it also requires a large amount of annotated data to train the model effectively.