Sentiment and emotion are often used interchangeably, however, they are in fact quite different. 

Sentiment analysis is a common feature of social listening and survey analysis tools. It classifies text as positive, neutral, or negative to generate a sentiment score that indicates how positively or negatively people are discussing a topic or brand. The objective of sentiment analysis is to provide a top-line assessment of an audience's feelings. The reliability of sentiment analysis is frequently impacted by the use of words in different contexts.

In Relative Insight, we use sentiment to deliver a Relationship Map - a visual representation of how sentiment and topics are interconnected. The thickness of each line corresponds to the strength of the relationship, providing insights into the connections within your data. This serves as a high-level summary, to help you uncover the areas that need further investigation.

Emotions, on the other hand, are complex characteristics that convey how people feel about what they are saying. Understanding this complexity will provide you with a new way to authentically engage and connect with your audiences. For this reason, advanced emotional analysis is an incredibly valuable source of insight that moves beyond what people are saying to how they are saying it.

In Data Discovery, Relative Insight visualizes the emotions expressed within the data in a treemap. It helps to give context by indicating how people feel about topics and themes.

Relative Insight's emotional analysis capabilities go deeper than sentiment analysis, enabling you to take a more sophisticated approach to understanding audiences.

For example, the platform will be able to tell you if one audience’s language use is more violent, angry, confident, or calm than another.

The platform is able to identify over 20 different emotions when analyzing a data set. It does this by looking not only at individual words but also at the surrounding words. This helps to capture context and supports the accuracy of emotional classifications.

In comparison to sentiment analysis, this allows for the identification of emotional nuances within the text analysis that are far more insightful than a positive-negative classification alone.