Sentiment Analysis leverages a Natural Language Processing (NLP) API or a Large Language Model (LLM) API to interpret and apply sentiment to unstructured data in open-ended responses. All clients have access to the NLP-based version by default; to unlock the enhanced LLM-powered sentiment analysis, AI and Skipper must be enabled for the account.

 

 

1. Interpreting Sentiments

1. From the Results page, click the Verbatim icon at the top  to view all responses to the open ended questions included in your survey. The colored bands along the left side of each comment box indicate the sentiment related to the response.
2. Hover anywhere inside a response to see the corresponding emoticon, and click the assigned emoticon to view the spectrum of sentiments.
   • Green (smiling face) represents a positive response.
   • Orange (unsure face) represents a mixed response.
   • Red (frowning face) represents a negative response.
   • Blue (neutral face) represents a neutral response.
   • Gray (no mouth face) represents none. 
3. Click on the icon assigned to a response, and select a different emoticon to change the assigned sentiment.
4. Click the gray icon to remove a sentiment from a response and assign it none.
5. Click the ellipses in the grey filter and search menu at the top of the page and uncheck the Show sentiment box to hide sentiments from the open ended responses. 

 

---

 

2. Globally Filtering with Sentiments 

Sentiments can be used as filters for open ended responses.

1. Click in the search bar and select a sentiment from the pop-up menu.
2. Click the search button to isolate sentiments of one type across all open ended responses in the survey.

 

---

 

3. Question level sentiment filters

1. Click on the filter menu in the left sidebar, and scroll to the open ended question you’d like to evaluate.
2. Click on the Sentiments drop-down that appears below the question, and select the sentiments you’d like to see.
   Note: This menu will only populate with the sentiments that have been applied to that question–e.g. if there are no Mixed sentiments found in the responses to that question, Mixed will not appear as an option.

 

---

 

4. Coding and Bulk Actions

Sentiments also appear as codes in the autocoding menu.

1. Click the Code icon in the left hand navigation to view any codebooks you’ve created, as well as codes associated with each sentiment.
2. Enter search terms into the search bar, and with the filtered results in view, click the settings wheel to the right of the desired sentiment.
3. Select Remove code from comments on page, or Remove code from all found comments, to remove sentiments in bulk.
4. Select Assign to multiple comments and then choose Apply to the number of comments displayed on page, Apply to all, or Cancel.

 

---

 

5. Turning off Sentiments at the question level

1. Click the Coding button in the left sidebar of the status page, and click the Sentiment Analysis On/Off drop-down box.
2. Deselect the question or sub question you’d like to turn off. The stats page will reload, with the sentiment disabled for the question you chose.

 

---

 

6. Custom Virtual Questions

1. Add a Virtual question, and click Switch to advanced mode above the first answer option.
2. Enter the logic tag.sentiment Q# = “positive/negative/mixed/neutral/none” into the text field. In this way, you can layer sentiments to create a custom Virtual Question.
   Note: It is important to reference the question number in this logic string, since sentiments are applied to all open ended responses in your survey.

Helpful Hint: To ensure you are using the correct logic for a sentiment code, go to the filters menu, enable the filter for the specific question and sentiment, and then click Switch to advanced mode. Copy the logic that appears in the Custom filters text box, and paste it into your Virtual Question. Remember to delete the text before switching back to basic mode, to find the logic for a different sentiment code.

 

 

---

 

7. Visualizing Sentiments

To see a quantified view of Sentiment Analysis:

1. From the Quant Report of the Results Page, scroll to an open-ended question.
2. Click the first drop-down menu, and select Sentiments. A bar graph will appear, displaying the distribution of sentiment across responses for that question.