Open text questions are a great way to get deeper insights from your respondents. They give people the freedom to explain their thoughts in their own words—but analysing those responses can be time-consuming. That’s why we offer several powerful tools to make open text analysis easier and faster.
AI Summary (New!)
Our AI summary generates a 3–5 bullet point overview of the key themes in your open text responses. It’s especially useful for longer, more detailed responses where you're looking for a qualitative summary of themes, rather than a quantitative breakdown. The summary adjusts to any filters or waves you’ve applied and is easy to copy and share.
Use it when you're working with longer responses and want a fast, high-level understanding of what’s being said.
Manual Keywords (New - in Beta)
With manual keywords, you can define your own tags for open text responses and use these in Split-by charts or crosstabs. This lets you compare what's top-of-mind across different groups or track specific themes like unaided brand awareness over time.
Use it when you need custom, detailed analysis—especially across time or demographics.
(Currently in limited beta – ask for access by reaching out to your Customer Research Manager or using the in platform live-chat).
Automated Keyword Analysis
Our automated keyword tool uses machine learning to surface the most mentioned words and group similar ones together. It also includes a word cloud view for quick visual insights, and you can merge or edit keywords manually. You can access this by clicking on "Keywords analysis" on the top right.
Use it when you want to quickly explore the data and get a visual overview. It's useful for questions where you are asking people for shorter answers, but you aren't sure yet what answers you'll get back.
How does automated keyword analysis work?
How does automated keyword analysis work?
We’ve spent months building and training our own data model for this feature, based on the millions of open-ended responses that we’ve gathered over the years.
There are two important steps in the way the model works:
Key phrase extraction
Key phrase grouping
The key phrase extraction algorithm is a deep-learning model that has been trained to extract important/relevant keywords in open text.
The key phrase grouping algorithm takes these key phrases and then groups similar key phrases into the same group. What’s unique about our key phrase grouping is that it isn’t just based on a simple text match, but based on deep-learning. This means that it’s able to also recognize terms that are semantically similar (for example, ‘amazing’ and ‘wonderful’).
We’re still aiming to further improve this model, so keep in mind that while it’s built on a solid foundation of data science, certain words might not be picked up by our AI model as a keyword. Also, while our model implicitly understands that words that are spelled similarly (i.e typos, doge <> dog) have a high similarity, this doesn’t mean that the model will be able to pick up on any type of spelling mistake.
Sentiment Analysis
You can see the sentiment analysis on for any open text question. It classifies responses as positive, neutral, or negative—helping you understand the emotional tone of the feedback.
Use it when you're interested in the overall mood or tone behind the answers.
