The error suggests that there is an issue with the dimensions of the input and the convolutional layer in your neural network. The error is caused by trying to subtract 5 from a dimension of size 1, which results in a negative dimension size.

This error occurs when the shape of the input to the convolutional layer does not match the expected shape of the weights of the layer.

I suggest you check the dimensions of your input data and ensure that they match the expected input shape of your convolutional layer. You may also need to adjust the hyperparameters of your convolutional layer, such as the filter size or padding, to ensure that they are compatible with your input data.

Dear Usman Rafi ,

It’s not difficult to use Scikit-learn to build machine-learning models that analyze text for sentiment, identify spam e-mails, and classify textual data in other ways. But state-of-the-art text classification is most often performed with neural networks. You already know how to build neural networks that do binary classification and multiclass classification using rows of numbers as input. Let’s build on that to learn how to construct deep-learning models that classify text.

https://www.atmosera.com/blog/text-classification-with-neural-networks/

Regards,

Shafagat

Dear Rafi,

For text classification, you first should convert text to vectors, using word2vec, doc2vec, BERT, etc. Then using ANN such as LSTM,BiLSTM, …you can classify textual features.

Usman Rafi I advise you this publication

On the Integration of Similarity Measures with Machine Learning Models to Enhance Text Classification Performance

Article On the Integration of Similarity Measures with Machine Learn...