The summaries and labels generated by AI Remark Labelling are automatically produced by an AI model based on the content of the remarks. While the AI aims to accurately categorize and summarize responses, the results may not always be fully precise or complete.
AI Remark Labelling
Introduction
The AI Remark Labelling feature automatically analyzes open-ended responses (remarks) and assigns descriptive labels. This helps organize qualitative feedback, making it easier to identify themes, patterns, and trends in panellists’ comments.
Instead of manually reviewing each remark, AI can quickly categorize responses and generate summaries.
How AI Remark Labelling Works
AI scans the text responses from selected questions and assigns relevant labels based on the content of each remark.
For example, if panellists describe their meals, AI can categorize the remarks using labels such as:
- dairy
- meaty
- vegan
- vegetarian
These labels allow you to quickly group similar responses and analyze them more efficiently.
Step 1: Select the Question
In the AI Remark Labelling section, choose the remark question you want to analyze. The AI will review all remarks submitted for that question.
Step 2: Choose the Labelling Mode
You can select how the labels will be generated.
Use Existing Labels
AI assigns labels only from the list you provide.
-
Enter the labels in the Labelling Text Input Field separated by commas.
-
Example labels:
dairy, meaty, vegan, vegetarian -
AI will classify each remark using only these labels.
This option is useful when you want consistent, predefined categories.
Let AI Generate New Labels
AI automatically creates the most appropriate labels based on the content of the remarks.
This option is useful when you want to explore themes without defining categories in advance.
Step 3: Configure General Settings
You can adjust additional settings before running the analysis.
Maximum number of labels per remark
Limits how many labels AI can assign to a single remark.
Result language
Choose the language used for the AI-generated output.
Step 4: Run the Labelling
Click Apply AI Remark Labelling to start the analysis.
AI will process the remarks and assign labels automatically.
Depending on the number of remarks, the analysis may take up to 5 minutes. You can leave this page while the AI processes the data.
Viewing the Results
Label Distribution
After processing, the system displays a chart showing how often each label appears across the responses including Sentiment Analysis . This helps quickly identify common themes.
For example:
- dairy may appear more frequently in breakfast remarks.
- meaty may appear more often in lunch remarks.
AI Generated Summary
The Summary tab provides an automatically generated overview of the remarks.
It highlights key trends and common patterns found in the responses.
The AI-generated summaries are automatically stored in the Product Properties of each product.
This allows you to include these summaries when exporting or printing your results.
If you want the summaries to appear in your reports, simply ensure that the Product Properties fields are included in your result templates.
This makes it possible to present both the quantitative results and the AI-generated insights together in your final report.
Labelled Remarks
Each individual remark is displayed together with the label assigned by AI.
Resetting or Running a New Analysis
You can modify your settings and run the analysis again at any time.
-
Reset Results – Clears the current AI labelling results.
-
Run New AI Labelling – Starts a new analysis using updated settings. This option can be used if you want to keep the existing AI labels while adding additional ones.
Benefits of AI Remark Labelling
-
Automatically organizes qualitative feedback
-
Reduces manual analysis time
-
Identifies patterns in large sets of remarks
-
Generates summaries and visual insights
Access to AI Remark Labelling
To activate this feature for your account, please contact: support@eyequestion.nl
Things to Consider
- You can run AI Remark Labelling multiple times within the same project. However, after completing an analysis, you must wait a few minutes before starting a new one. This waiting period ensures that the system has finished processing the previous task before a new analysis begins.
It is recommended to review the generated labels and summaries before using them in reports or decision-making. AI-generated insights should be considered as supportive analysis rather than a definitive interpretation of the data.
Related Articles
How to Use Remark Labeling
Introduction Open-ended comments provide valuable insights into the consumer's perception of a product, and help in identifying areas for improvement. However, analyzing such comments can be time-consuming and challenging. With remark labeling, the ...Remarks Representation
Purpose The remarks representation method can be used to display remark and comment data. Options Split Results On: Choose to split your results on either Judge, Attribute, Product or Session. Alternatively, choose None if you do not wish to split ...Text Highlighting
Introduction The text highlighting is a novel method for explicit attitude measurement. This method leverages the natural, intuitive action of highlighting to gauge participants' attitudes. Participants are shown a piece of text and are asked to use ...Data Cleaning
Introduction Following data collection, it's essential to ensure the validity of the collected data and address any instances where participants may have completed the questionnaire without due attention. To tackle this issue, we've introduced a ...How to Show Panellists their Answers
Introduction In the following article we outline the possibility for panellists to review and modify, if necessary, their answers before submitting the questionnaire. This ensures that the answers they provide truly reflect their views and are as ...