If you're using a regular classification algorithm like SVM, it's not very surprising that the model fails to find any indication in the features if the features consist only of the word and this boolean feature.
This kind of task is usually done with a sequence labelling model like CRF: such models learn indications from the context of the sentences in ...
For starters you can find the correlation of each column with the output column and select the features which are highly correlated .This will also help you to remove features which will not contribute towards learning weights and biases .
fixed acidity 0.119024
volatile acidity -0.395214
Yes it will definitely affect the result. If you are going to use CNN pre-trained models for feature extraction you have to remove the last output layer.
Along with that you have to remove all the densely(Fully) connected layers since those will act as ANN for processing to predict the results.
We need only the features to be trained using other models like ...