Sentiment analysis uses blocks of text to predict a positive or negative sentiment for the text

Select a DSD to use for training. Only those with a purpose of “Machine Learning” will be shown.

Select the Data Group within the DSD that contains the training data.

Two further entries are required:

• Sentiment Text – the field that represents the blocks of text to be analysed
• Sentiment – the field that represents the sentiment for each text

If the model has been trained before, the right hand side of the page shows the metrics of that training. See below for more information on metrics.

Save the training settings and the click on “Train”

For Sentiment training, there are no settings.

Click Start to begin the training.

On completion metrics for the training will be shown.

• Log Loss – quantifies the accuracy of the model – the closer to one the better
• LogLossReduction – measure of improvement over random – the closer to one the better
• Entropy - a measure of the level of disorder or uncertainty – the closer to zero the better
• AreaUnderRocCurve – area under curve between true positive rate and false negative – the closer to one the better
• Accuracy – proportion of correct predictions to total samples – the closer to one the better
• PositivePrecision – proportion of correct positive predictions– the closer to one the better
• PositiveRecall – proportion of correct positive predictions among positive instances - the closer to one the better
• NegativePrecision – proportion of correct Negative predictions– the closer to one the better
• NegativeRecall – proportion of correct Negative predictions among Negative instances - the closer to one the better
• F1Score – a measure of quality - the closer to one the better
• AreaUnderPrecisionRecallCurve – measure of success when classes or imbalanced - the closer to one the better

Enter a sample block of Sentiment Text to receive a predicted Sentiment.