Skip to main content

Text AI – Sentiment Analysis

Learn about the sentiment analysis feature that automatically classifies open-ended text responses into positive, neutral, and negative sentiments, how to run it, and how to use the analysis results.

Updated today

📌 Text AI is available on the Professional or Enterprise plan.

What Is Sentiment Analysis?

Sentiment analysis is a feature that helps you quickly determine whether responses overall are generally positive or whether negative opinions are prevalent, without having to read through each open-ended text response. AI analyzes the expression and nuance of each response and automatically classifies it into one of three sentiments — positive, neutral, or negative — with results visualized in a gauge chart so you can see the overall tone at a glance.

🧙 Understanding sentiment analysis through an example

"I asked for reasons for satisfaction or dissatisfaction with Brand A's products, but there are so many responses it's hard to tell at a glance whether the overall tone is positive or negative. 🤔"

Running sentiment analysis in this situation has AI analyze the meaning of each response and automatically classify sentiments.

  • 'Great sound quality,' 'Good value for money' → Positive

  • 'Battery doesn't last long' → Negative

  • 'It's adequate' → Neutral

Since responses are classified into positive, neutral, and negative categories with the ratio of each sentiment also displayed, you can quickly see the overall flow of opinions.


How to Run Sentiment Analysis

📌 Sentiment analysis deducts 1 text credit per response.

1️⃣ Launch AI analysis 'Ossistant'

step 1. In the variable list on the left sidebar of the Text AI tab, select the text variable to analyze, then click the [AI Analysis] button in the upper right.

step 2. When the chatbot Ossistant appears, follow Ossistant's guidance and select 'Sentiment analysis.'

💡 Usage tip | 'Sentiment analysis' is only activated when text data is present.

3️⃣ Start the analysis.

step 1. Before running the analysis, check the number of responses to be analyzed, the analysis feature, and the credits to be deducted.

step 2. Select [Yes] to proceed. The analysis starts and generally completes within 2 hours.

  • Analysis generally completes within 2 hours; for 1,000 or more responses, it may take up to 24 hours.

  • Even if you close the browser window after requesting analysis, the analysis continues.

step 3. Once analysis is complete, the results are visualized in a gauge chart so you can review the overall emotional tendencies.


Using Analysis Results

1️⃣ Check sentiment ratios with the gauge chart

Once analysis is complete, a gauge chart is displayed below the word cloud. The count and percentage of responses by sentiment are visible at a glance, with the number of positive responses highlighted in the center.

💡 Usage tip | The gauge chart can be downloaded as an image.

2️⃣ Identify causes with response summaries

step 1. In the response summary area at the bottom of the chart, you can review a summary of the key content for each positive, neutral, and negative sentiment.

step 2. Clicking the [∨] button for each sentiment lets you view a portion of the original responses classified under that sentiment.

3️⃣ Compare groups with cross-tab analysis

step 1. Click the [Cross-tab] icon in the sentiment analysis results area.

step 2. In the cross-tab screen, the variable generated through sentiment analysis is automatically added as the analysis target. Adding the desired group or variable as analysis criteria here lets you compare and review sentiment analysis results by criteria.


Frequently Asked Questions

Q. What is the 'Unclassified' view?

A. Responses where the expression or context makes it difficult to clearly classify them as positive, neutral, or negative are displayed as 'Unclassified.'

To help you quickly grasp the overall emotional flow, unclassified responses are excluded from the default results screen. If needed, turning on the [View Unclassified] toggle lets you also view unclassified responses.

Q. Can sentiment analysis results be viewed in other tabs?

A. Yes, they can. When sentiment analysis is run, a new variable is generated in the format (variable name selected for topic analysis)_topic analysis run date.

This variable can be reviewed and used not only in the Text AI tab, but also in the Results tab, Cross-tab tab, and Report tab.

This allows you to compare sentiment results by group or organize analysis content into report materials.


Have you got a good understanding?

If you still have questions after reviewing this guide, please contact us anytime via the [Help Center icon] in the bottom right corner of your screen. Our team will do its best to help you resolve any difficulties you're experiencing.

Did this answer your question?