Keywords: emojization, sentiment analysis, emotion recognition, emotion labels
While sentiment analysis is useful for capturing the sentiment orientation (positive, neutral, negative) in text, and emotion recognition can be used to identify emotions such as joy and frustration, the Emojize operation provides a higher level of nuance. It interprets the emotional tone in text and expresses it in the form of the most appropriate among the 64 most common emojis. The operation outputs these emojis with labels.
The operation relies on a deep learning model that was trained on 1.3 billion English tweets and is further described in this paper.
1. Open the operation configuration window
Select the text field that you want to run emojization on and click the "Add operation" button at the top of the workspace.
Search for "Emojize" or find the operation under "Text enrichment" and click it.
2. Specify language
In the "Language" drop-down, select the language of your input text. Currently English is the only language available.
3. Name the output collection
Under "Output collection name", type the name of the output field.
4. Run the operation
Click "Apply" to run the operation. The output emojis are inserted into the "value" subfield, their corresponding text labels into the "description" subfield, and their accuracy score for each input text into the "score" subfield.