Score text is an operation that compares a selected text field with the provided text or keywords based on the number of occurrences or semantic similarity between them. The operation offers three approaches to score text: average semantic similarity, maximum semantic similarity, and occurrence score.
The average semantic similarity method checks the similarity score of each defined keyword with input texts in the selected column and takes their average to set the score.
The maximum semantic similarity method checks the similarity score of each defined keyword with input texts in the selected column. It assigns the highest score according to the most related keyword.
The occurrence score method takes the quantitative approach as a base. The text is scored based on the overall frequency of the keywords used. If you provide multiple keywords, it assigns a higher score to the keywords that have similar distributions in the text.
1. Open the operation configuration window
Select the text field you want to score and click the "Add operation" button at the top of the workspace.
Search for "Score text" or find the operation under "Text enrichment" and click it.
2. Select the score text method
Three options are available: "Average semantic similarity," "Maximum semantic similarity," and “Occurrence score.” See the description of each method above.
3. Define keywords or the text
After that, choose scoring either by keywords or by text. By keywords option enables you to score the text by considering various keywords, whereas by text option is scoring the text by checking the complete defined sentence or phrase.
4. Name the output field
Under "Output field name,” type the name of the output field. The output field will contain decimal values.
5. Apply the operation
Click "Apply" to run the operation. As a result, the Score field is created, which is visible on the Schema. You can view the set scores according to the keyword and the chosen scoring method on Table View.