The sentiment_analysis service can be used to apply sentiment analysis on the audio any text input. With the use of dialogflow, the sentiment_analysis service can process the audio input given by an user. By using this service together with the Dialogflow service, sentiment analysis can be run on the audio input of a user (i.e. speech). Making use of a Naive Bayes Classifier , sentiment_analysis can classify from the Natural Language Toolkit (NLTK), this service classifies a sentence as either being positive or negative. This service is built using the Natural Language Toolkit (NLTK) package from python.
Since this service is still being worked on, it should be noted that this Naive Bayes Classifier it is trained on a dataset consisting of 10000 random twitter samples from Twitter. Therefore, in some cases the service is still performing poorlydoes not perform very well.