Need Help?

Emotion Analysis

Last Updated: May 16, 2017

Sentiment Analysis
Positive. Negative. Neutral.

How primitive.

Traditional text analytics solutions perform sentiment analysis. This method consists of identifying the occurrence of positive and negative sentiment terms in data and taking the average, resulting in thumbs up, thumbs down, or neutral scores.

This type of solution glosses over complex expressions of human emotion, thereby missing valuable business insights. Even promoters have criticisms and detractors often provide positive insights. For example, one favorable review might go as follows:
"We love the Eatery on Main Street! We go there at least once a week. The service is terrific and the food is awesome! But we went for dinner on a Friday and it was really crowded. Plus, our steaks took a long time to cook. The service was slower than usual... But they gave us a free glass of wine and we ended up being really happy."
This is a typical crowd-sourced review full of nuance and specifics. Most text analytics generate a thumbs down or perhaps a neutral score from that review. Yet overall, that was actually a glowing review that contains important, actionable business insights. So as a result, a decision-maker might get a report from a data set of such reviews resulting in 25% positive reviews, 45% neutral, 30% negative from traditional sentiment analysis solutions.
So besides being misleading, what is actionable from that kind of traditional analytics report? What could you do, specifically, to improve the customer experience with that information? Nothing. 

Luminoso captures the full spectrum of human emotion.
That's why we do Emotion Analysis in order to identify specific concepts and patterns in order to make smarter, more targeted business decisions.

You want to create more long-term loyalty for your customers, not just chase the next transaction. And you can only do so by having a more comprehensive understanding of your business by leveraging specific insights derived from complex human emotion.


Spotlight wins quickly. We often see the terms frustrated and disappointed across different data sets. Luminoso makes a distinction between these discrete emotions and allows you to quickly distinguish what, exactly, each emotional term is related to, as well as how strong those associations are.
What do we mean? People are often frustrated with a feature or function that isn’t working properly. But they can be disappointed in a product that lacks a feature in the first place. The differences we see in associations between those two terms is striking and consistent across data sets. Many expressions of (especially negative) emotion can lead to specific, actionable nuances. These important insights are quickly visible and measurable in Luminoso. 
Our software’s ability to discern complex and differentiated feelings, reactions, and sensations, as well as measure their associations against any other concept, is why we refer to
Emotion Analysis. Watch the video on Plutchick's wheel and how to perform an emotion analysis in Luminoso.


More Support
seconds ago
a minute ago
minutes ago
an hour ago
hours ago
a day ago
days ago
Invalid characters found