Would be good to have the results broken down by sentiment class using Macro F1 score. The F1 Score of the Positive, Negative, and Neutral sentiments. Might be good to have that for the accuracy as well. This would be useful so that we can see how well the model might be performing in the different classes.
Would be good to have the results broken down by sentiment class using Macro F1 score. The F1 Score of the Positive, Negative, and Neutral sentiments. Might be good to have that for the accuracy as well. This would be useful so that we can see how well the model might be performing in the different classes.