
One common question type in surveys is “free-text.”
For example, in the survey data below, there is a column for free-text responses such as “Reason for Recommendation.”

Previously, it was common to group text using the “Topic Model” feature in Exploratory’s Analytics view. However, topic models automatically extract topics from data, making it impossible to label text into predefined specific groups.
Furthermore, when attempting to label text using methods other than topic models, the following issues arise:
“AI Functions,” newly introduced in Exploratory v14, solve these challenges, enabling anyone to create AI-powered functions. Without any programming knowledge, you can easily create custom AI functions by simply writing instructions (prompts) in your own words.
This feature leverages state-of-the-art AI in the backend, allowing users to benefit from its powerful analytical capabilities without the hassle of complex configurations or model building.
The AI individually assesses each data row and returns the result as a new column, making it possible to assign appropriate labels and group free-text comments.
This makes advanced text data analysis, previously difficult for non-experts, accessible to all business users.
Here, we will specifically look at how to classify free-text responses, such as “Reason for Recommendation,” into specific groups using AI Functions.
You can download the data to use from here.

From the column header menu, select “Create AI Function.”

This will display the AI Function dialog.
The
prompt is specified and executed as follows:
Please assign labels to categorize the provided text into the following groups:
Good Support
Bad Support
High Product Rating
Low Product Rating
High Rating for Features
Low Rating for Features
Comparison with Competitor Services
Implementation-Related Content
Pricing-Related Content
Other

When this prompt is executed, the AI reads the provided free-text responses and assigns the most appropriate label from the 10 specified groups to each row.
For
example, a response like “The support staff was quick and polite” will
be assigned the label “Good Support,” while “The new feature is
difficult to use” will be assigned “Negative Feature Review.”
The results of sampling rows for each group are shown below, confirming that the AI successfully differentiated between good and bad support.

By classifying text with AI in this manner, it becomes possible to efficiently and objectively analyze customer feedback, quickly gaining specific insights that directly lead to product improvements and service enhancements.
Exploratory v14’s “AI Functions” revolutionize data analysis, enabling anyone to perform advanced processing using AI.
Exploratory v14’s “AI Functions” is a feature that can elevate your data utilization to the next level. We encourage you to experience it for yourself.
You can try out the latest features of Exploratory, including AI Functions, with a 30-day free trial.