Semi-Open Mode: Quick Guide

What is Semi-Open Mode?

Semi-open mode is designed for structured open-text questions where responses follow a limited and repeatable pattern.

Typical use cases:

• Brand awareness (“Which brands do you know?”)
• List-based answers (products, competitors, sources)
• Short, repetitive responses (often 1–3 words)

Instead of exploring themes, Semi-Open focuses on:

• standardizing similar answers
• grouping variations of the same term
• creating clean, consistent categories

Important: Selecting Text Columns 

Before starting the analysis, define your columns based on your use case:

Option 1: Analyze columns separately

• Select each column as Text-to-Analyze (TTA)
• Use this if you want to compare results across questions

Option 2: Combine columns 

• If your data is split across multiple columns, you can combine them using Smart Columns after import.
  
  

 Use this if:

• the columns contain the same or very similar question
• you want one unified analysis

Starting Analysis

You can choose:

Start from scratch

• AI generates initial topics and categories

Reuse existing structure

• Import a topic collection
• Reuse categories from another project

Key Settings

Term Similarity

Controls how strictly terms are grouped

• 100% → exact matches only
• ~75% → groups similar variations (e.g. spelling differences)

Minimum Count

Defines how often a term must appear to become a topic

• Example: 2 → only terms mentioned ≥2 times are separate topics

“Other” Topic Options

Controls how low-frequency responses are handled:

• None → no “Other” topic
• Unassigned Rows → only responses without a topic
• Rare Terms → low-frequency terms grouped into “Other”

Final Step: Review Topics & Keywords

Before finalizing your analysis, it’s important to review and fine-tune your topics and keywords. This ensures your results are accurate and aligned with your goals.

Review Topics

Start by checking the generated topics:

• Make sure each topic clearly represents a distinct answer or concept
• Rename topics if needed to improve clarity
• Merge similar topics to avoid duplication
• Remove any irrelevant or incorrect topics

Adjust Keywords

Each topic is supported by keywords that help the AI assign responses correctly.

To edit keywords:

• Click on a topic
• Open the keyword list
• Add or adjust terms as needed

Keywords help ensure that all relevant responses are grouped correctly, especially when answers vary slightly.

Best practices:

• Include abbreviations
  → e.g. “FB” for Facebook
• Add spelling variations
  → e.g. “McDonalds”, “Mc Donald’s”
• Include common phrasing
  → different ways users might refer to the same concept
• Be specific when needed
  → especially for similar or overlapping topics

Important: Focus on Structure, Not Individual Rows

In Semi-Open mode, you do not need to review every individual response.

Instead, focus on:

• making sure topics are correct
• ensuring keywords capture all relevant variations

This approach keeps your analysis:

• efficient
• scalable
• consistent

Video Guide

For a full walkthrough: