Find Insights: Sentiment

Sentiment analysis identifies whether the context of a text is positive, negative or neutral.


How can sentiment analysis be beneficial

Sentiment analysis focuses on the polarity of a text (positive, negative, neutral) and has been proven helpful for businesses in detecting sentiment in the received feedback which leads to a better understanding of needs and goals.

What are sentiments in natural language processing?

Traditionally sentiment analysis was a binary decision (Positive or Negative) but in more recent years, text polarity is defined as positive, negative and neural. Read more at What is sentiment analysis.

What comes with sentiment analysis at Relevance AI?

After running sentiment analysis workflow, results will be added to your dataset. This includes two fields:

  • Score: The confidence score on the decision made by AI on the polarity of the text
  • Sentiment: A string field containing one of the three labels positive, negative or neutral

Sentiment representation in Relevance AI

There are various ways one can benefit from and represent sentiment analysis results with full guide available at how to present sentiment on the Explorer dashboard. We mention the most common ones here.

Filter by sentiment

The sentiment field can be used as a filter. For example, in a customer feedback dataset, this helps to understand what areas are the ones that clients are happy about, and which points are the ones that need to be improved. You can follow the links to read more about how to set filters on the Explorer dashboard.

Relevance AI - Sentiment filter

Relevance AI - Sentiment filter

Sentiment timeline

A great tool to identify the trends and changes in positiveness or negativeness of the collected data.

Sentiment overview

A great tool to observe an overview of the data from sentiment perspective.

You can follow the links to read more about setting up sentiment charts