Sentiment extraction is the process of inferring user sentiment (positive, negative, or neutral) from text (typically call center logs, forums, and social media).
|SentimentTrainer (ML Engine)||Trains model—takes training documents and outputs maximum entropy classification model.|
|SentimentExtractor (ML Engine)||Uses either classification model or dictionary model to extract sentiment of each input document or sentence; that is, to output predictions.|
|SentimentEvaluator (ML Engine)||Uses test data to evaluate precision and recall of predictions.|
The sentiment extraction functions support English, Simplified Chinese, and Traditional Chinese text.