A large amount of information is available in the form of text. For example, tweets, emails, survey responses, product reviews and so forth contain information that is written in natural language.

The goal of working with text is to convert it into data that can be useful for analysis. Some applications of text analysis include: sentiment analysis, document clustering, named entity recognition, disambiguation, and so forth.

The following table lists available plugins that you can use to work on text data.


Not supported: These plugins are Not supported features

Plugin Description
Sentiment analysis Estimate sentiment polarity (positive/negative) of text
Named entity recognition Obtain useful information from text data by extracting named entities (such a, people, dates, places…)
Sentence embedding Compute numerical sentence representations for use as features in a machine learning model or for comparing texts
Text summarization Automatically summarize text data