Audience Fluency

Canvs 200% More Accurate Than Traditional Sentiment Analysis



Millennials have a unique perspective, and they’re not shy about sharing it. In fact, 56% of Millennial Twitter users say they use it to share personal information and chronicle their lives. They also state that Tweeting about an event makes it more enjoyable [1]. That includes watching TV: according to YuMe’s 2014 Mix & Measure Report, 92% of Millennials access a connected device while watching shows [2].

The value of following these Millennial conversations is enormous and growing. Forbes states that Millennials could account for $1.4 trillion in spending, or 30% of total retail sales, by 2020 [3]. It’s no surprise that this opportunity has sparked a race to discover the best technology and processes for tracking and analyzing social conversations.

As the industry standard for emotion measurement, Canvs has amassed a wealth of experience studying Millennial conversations, including a knowledge base of over five million expressions, acronyms, slang, misspellings, and emojis not found in the dictionary. We believe that this knowledge base and our proprietary technology for capturing “Emotional Reactions” (ERs) give Canvs an undisputed advantage over the so-called “sentiment analysis” offered by leading social listening platforms.

To prove the superiority of Emotional Reaction measurement over sentiment analysis, we conducted the following research experiment focused on MTV’s Teen Wolf series.


Teen Wolf is a series popular among Millennials [4], frequently holding the #1 position in its time slot for female viewers ages 12-34. We used social conversations revolving around the Season 5 finale to compare Canvs’ social TV suite to an industry-standard implementation of the SentiWordnet Sentiment Analysis built on top of the WordNet project from Princeton University.

Our hypothesis was that Canvs would show greater accuracy and depth of understanding.  

Key findings

We found that sentiment analysis was unable to understand 67% of Millennial’s Emotional Reactions to the Teen Wolf finale. Unlike Canvs, sentiment analysis offers a simplicity of analysis and is not able to keep up with the ever-evolving pace of social TV vernacular. Our results concluded that Canvs emotion measurement understood more accurately how Millennials felt than traditional sentiment analysis.


Canvs was 200% more accurate than sentiment analysis at parsing through how Millennials felt about the Season 5 finale of Teen Wolf.


If you take 100 Emotional Reactions as defined by Canvs, sentiment analysis missed 55, miscategorized 12, and correctly identified 33.



OMG and WTF accounted for more than 13% of all Emotional Reactions to the S5 finale of Teen Wolf, which sentiment analysis altogether ignored as indicative for analysis.



In order to accurately understand one of the most important demographic groups – Millennials – you have to understand the nuances of the language they use to express emotions in social media. The unique vernacular that Millennials use is one of the distinguishing attributes of this generation. Because of this, Canvs is uniquely positioned to not only comprehend Millennials, but their emotional investment to content, as well.

Learn More about How Canvs Measures Emotions

[1] Moy, Aaron. “Four insights about millennials on Twitter.” Twitter. 09 July 2014.

[2] Marshall, Carla. “92% of U.S. Millennials Turn to Second Screens While Watching TV.” reelseo. 05 June 2014.

[3] Shin, Laura. “How The Millennial Generation Could Affect The Economy Over The Next Five Years.” Forbes. 30 April 2015.

[4] “MTV’s ‘Scream’ Premiere Grows to 6 Million Cumulative Total Viewers in Live +3 Ratings.” TV by the Numbers. 06 July 2015.