How to Calculate Sentiment Scores for Open-Ended Responses Using R

Displayr uses R to calculate the Sentiment Score from text variables. All R variables in Displayr must be calculated within two minutes by default. However, in some instances, when working with large data files and longer open-ended text responses, the analysis takes longer to run, resulting in a time-out error. This article explains what to do in these cases.

Requirements

A Text variable. Text variables are represented by a small a next to the variable in the Data Sources tree:

Method

1. From the toolbar, go to Calculation > Custom Code.
2. Click on the page to place the custom calculation.

3. Paste the following code into the Code panel:

   library(flipTextAnalysis) 
   
   #Define variable name, which can be found in General > Name
   input <- Likes 
   
   #Calculate the Sentiment Scores
   sentiment.scores <- SaveNetSentimentScores(input, check.simple.suffixes = TRUE, blanks.as.missing = TRUE)

   You will need to update "Likes" on Line 4 with the Name of your input text variable. 

4. Click Calculate.
5. Hover over any variable in the Data Sources tree and click Plus (+) > Custom Code > R > Numeric.
6. In the Code panel for the variable, click the name of the output calculated in step three to reference the data. In this case, the output should be called sentiment.scores.
7.  Click Calculate.
8. In Properties , go to the General tab and update the variable Label and Name.
9. The resulting numeric variable can be used to show the sentiment score.

Next

How to Calculate Sentiment Scores for Open-Ended Responses

How to Show Sentiment in Word Clouds