Sentiment extraction is the process of inferring user sentiment (positive, negative, or neutral) from text (typically call center logs, forums, and social media).
| Function | Description |
|---|---|
| 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.