Join the next Canvs AI Product Tour ->
Canvs AI Logo

Emotion Measurement Methodology

One of the most important indicators of a person's true thoughts, intentions, and motivations is emotion. At Canvs, our mission is to make it possible to to capture, identify, and measure emotions in written communications with superhuman accuracy. Our patented technology and knowledge base of trillions of terms makes Canvs the industry standard in emotion measurement.

Our Key Metric

Emotional Reactions

Human emotions are rich and diverse. Some estimates show that we can express up to 1,000 nuances of emotion. At Canvs, we excel in identifying those feelings as they occur in language and categorizing them as specific Emotional Reactions. An Emotional Reaction is our proprietary metric for an explicit textual expression of an emotion, such as Happy, Sad, Funny, Excited, Crazy, or many more.

Un-Natural Language Processing

As linguistic anthropologists, we are fascinated by the diverse and ever-changing ways in which people express their emotions in words. Especially the elusive Gen Z and Millennial audiences who spend so much time in social and online conversation. Our quest to understand them drove us to develop our one-of-a-kind unnatural language processing engine, which recognizes trillions of words and expressions, including slang, acronyms, emojis, misspellings, and subtle nuances such as sarcasm and “shade.” In fact, 65% of the emotions we track aren’t even in the dictionary.

Where other people and platforms just see nonsense and contradictions, Canvs hears audiences telling you exactly what they think and feel about your products and services.

Vastly Superior to Sentiment Analysis

Sometimes people Tweet using more than one emotion in a given piece of content.

Most social media analytics companies offer simplistic measuring capabilities that do not account for these complexities and put emotions into generic, meaningless buckets: positive, negative, neutral.

Only Canvs offers the patented approach of categorizing written content into a full spectrum of Emotional Reactions. We accomplish this with a mixture of science and judgment, a unique approach to quantitative analysis developed by Dr. Sam Hui, our lead data scientist and co-founder.

This consists of using natural language processing and semantic analysis to locate and categorize Emotional Reactions in text. And then using machine-learning assisted technicians to analyze the output, make judgements about newly identified terms, and update the knowledge base (currently at trillions of terms) in order to make Canvs unbelievably accurate.

Canvs AI text analysis methodology diagram

In developing and refining the Canvs platform, we’re guided by the SIFT framework



Algorithms are only as good as the assumptions upon which they’re built. That’s why Canvs adds a human touch to help curate results at scale. That’s vital for long-lasting quality control. It also allows us to constantly improve in an iterative and agile fashion. For example, as soon as people start using a new phrase (e.g., ‘on fleek’) that is captured by Canvs, we add it into our algorithm. The next time our system observes it in text, Canvs can actively read and appropriately attribute it.



Canvs is the industry standard in understanding how people are Emotionally Reacting to content by taking short form text and aligning it to core emotions. It’s that simple. By keeping our methodology a straightforward mix of science and judgment, we ensure we’re the experts at the value we’re able to provide to the industry.



Canvs filters the results into ready products that clients can use to make smart, actionable decisions by distilling the data into useful, digestible breakdowns of emotions.



Canvs takes the core emotions that we identify and outputs them in a meaningful, actionable, and verifiable manner. The core emotions are familiar, and our key metrics, Emotional Reaction and Reaction Rate, are transparent measures based on the data inputs.

Canvs is a living and breathing entity. We are constantly evolving our database to ensure we are accounting for the latest slang and terminology and lingo being used across platform. We’ve perfected this system to such a degree that now emotions can be compared against any dataset with a level of standardization truly unique to the industry.


Schedule a demo

See how Canvs automates text analysis, saves time, and improves insights from open-ended text!


Almost there...

Please complete the information below to access this content.


See Canvs in action

Schedule a demo to see how Canvs automates text analysis, saves time, and improves insights from open-ended text!