Skip to main content
TRAC: Emotion Analysis

For more information on everything emotion-related, read here!

Updated over 3 months ago

Learning Outcomes

  • You will learn what Emotion Analysis is.

  • You will see where you can find emotion analysis within TRAC.

  • You will learn about the range of emotions we can assign to content on Pulsar.


What is Emotion?

Emotion Analysis is a standard part of natural language processing and involves analyzing the underlying emotions expressed in text. These emotions can range from joy, excitement and surprise to fear, hate and disgust.

On Pulsar Emotion analysis currently works on English content. Every post from X, Instagram, Tumblr, Youtube, Blogs, Forums, Reviews, News sites receives an emotion score if we can detect signals strong enough to be classified in one of 5 emotions. These 5 emotions are

  • Anger

  • Disgust

  • Fear

  • Joy

  • Sadness.

The Emotion classifier returns a confidence score for each Emotion that has been detected in the post. The confidence score indicates the probability that the corresponding emotion is implied by the text. Each post will contain emotion keys and score values (0.0 to 1.0). If a score is above 0.5, then the text can be classified as conveying the corresponding emotion.

πŸ“ Note: We currently only support Emotion analysis for English contents.


Where can Emotions be found?

Emotion analysis on Pulsar can be found in a number of sections, including the following:

Emotions Over Time

The Emotions Over Time graph is grouped by Volume, Visibility, Media Reach, or Social Impressions.

  • Emotions chart by Volume: This view measures and breaks down the Volume of posts and engagements that contain anger, disgust, fear, joy or sadness within the selected time frame. Each post counts as an "occurrence".

  • Emotions chart by Impressions: This view measures and breaks down the Social Impressions generated by posts that contain anger, disgust, fear, joy or sadness within the selected time frame.

  • Emotions chart by Media Reach: This view measures and breaks down the Media Reach generated by posts that contain anger, disgust, fear, joy or sadness within the selected time frame.

  • Emotions chart by Visibility: This view measures and breaks down the Visibility of the posts that contain anger, disgust, fear, joy or sadness within the selected time frame.


Keywords Emotions Word Cloud

The Keywords Word Cloud chart shows the most common keywords in a search and the emotion associated with those keywords. The bigger the size of the keyword and the more central it is in the graph, then the greater the number of posts and articles containing that term.


Hashtags Emotion Word Cloud

The Hashtags Word Cloud chart shows the most common hashtags in a search and the emotion associated with those hashtags. The bigger the size of the hashtag and the more central it is in the graph, then the greater the number of posts and articles containing that hashtag.


Topics Emotion Word Cloud

The Topics Word Cloud chart shows the most common topics being discussed in a search and the emotion associated with those topics. Topic analysis on Pulsar is based on a top-down taxonomy led classification, which identifies the main themes in a document, even if they aren’t explicitly mentioned. The bigger the size of the topic and the more central it is in the graph, then the greater the number of posts and articles about that topic.


Entities Emotion Word Cloud

The Entities Word Cloud chart shows the most common entities in a search, and the emotion associated with those entities. Our entity classifier identifies People or Organizations being discussed in a post, as well as People or Organizations mentioned in a TV, Broadcast or Podcast clip. The bigger the size of the entity and the more central it is in the graph, then the greater the number of posts and articles discussing that entity.


We hope you enjoyed reading this article! πŸ“š

If you have any questions or would like to learn more, please don't hesitate to reach out to our support team via live chat. πŸš€

Did this answer your question?