I have a model for binary classification that includes 2 linear layers with RELU activation function and Sigmoid in the last layer. The input features are FastText word embedding, frequency, and statistical signals.
This model has a 93% f1-score and I want to add an explanation to this model but I don't know how can I start.
My question is which models or papers good for these complex input features?
I appreciate any advice to achieve this goal.