> For the complete documentation index, see [llms.txt](https://ailyze.gitbook.io/ailyze-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ailyze.gitbook.io/ailyze-docs/common-research-workflows/analyze-open-ended-survey-responses.md).
# Analyze Open-Ended Survey Responses
This page shows you how to make sense of free-text survey answers held in a **spreadsheet** — each row a respondent, each column a question. This is the deepest workflow in Evidano because it has **two analysis paths** that produce **two kinds of results**. Choosing well is the most important decision, so we'll cover it carefully.
{% hint style="info" %}
**What you need:** A Free or Pro plan, and one spreadsheet (XLSX or CSV) with respondents as rows and questions as columns.
**What you will have at the end:** Coded themes for your open-ended questions, charts for every question, and comparisons across respondent groups.
{% endhint %}
## Step 1: Prepare your spreadsheet
* One **XLSX or CSV** file, **one file per project**, up to about **5,000 rows**.
* **Row = respondent, column = question.** Include any demographics (age, region, department) as their own columns — you'll use them as [segments](/ailyze-docs/reference/glossary.md#segment).
* A respondent **name or ID** column is helpful for quote attribution.
## Step 2: Choose your analysis path (the key decision)
After upload, **"Choose the type of Analysis"** offers two real paths.
### Path A — "Analyze … survey data across all columns"
*Each row is a survey response; each column is a survey question.*
Choose this to analyze a **whole survey**. Evidano produces:
* one **Overall** survey project (a dashboard summarizing *every* column), **plus**
* one **separate thematic project for each open-ended (text) column**.
{% hint style="info" %}
So one click can create several projects. That's expected — the success message spells out exactly what you'll receive.
{% endhint %}
### Path B — "Analyze text responses in selected columns"
*Organize specific open-ended responses into themes.*
Choose this when you only care about **one or a few free-text questions** (for example, "What's the main reason for your score?"). You get **one focused thematic project** per selected column.
### "Analyze interview data" (not a survey path)
Selecting this just tells you to use the docx/pdf workflow instead — it's a redirect, not a spreadsheet analysis. See [Analyze interview transcripts](/ailyze-docs/common-research-workflows/analyze-interview-transcripts.md).
> **Which should I pick?** Want a full survey report with cross-tabs (tables that compare groups side by side) and per-question charts → **Path A**. Want to deeply code a couple of open-ended questions → **Path B**. More guidance: [Choosing the right analysis approach](/ailyze-docs/methods-and-best-practices/choosing-the-right-analysis-approach.md).
## Step 3: Configure Path A (all columns)
### Configure column types
Evidano auto-tags every column; you review and **drag and drop** on the **"Configure Column Types"** board into six buckets:
| Bucket | What Evidano does with it |
| ---------------------- | -------------------------------------------------------------------------------------------------------------------------------------------- |
| **Numerical Data** | Displays as histograms (bar charts of value ranges) |
| **Categorical Data** | Displays as bar charts |
| **Text Data** | Codes into [themes](/ailyze-docs/reference/glossary.md#theme) / [sub-themes](/ailyze-docs/reference/glossary.md#sub-theme), shows bar charts |
| **Segments** | Compares the other data **across** these groups |
| **Respondent Name/ID** | Used when citing quotes |
| **Not Analyzed** | Ignored (timestamps, collector IDs, consent, etc.) |
To compare results by department, region, tenure, usage frequency, and so on, **drag those columns into Segments**. Each bucket has a **"Sample analysis you will get"** preview.
### Configure text analysis
For text columns, click **"Configure Text Analysis"** → **"Use AI to Identify top themes and sub-themes"** (or supply your own). You can add optional report instructions like *"the data is post-purchase feedback for a mobile app."*
### Submit
Click **"Create Project and Start Analysis"** (or the survey-wide button **"Analyze numerical, categorical, text, and segment data, and create survey report"**).
## Step 4: Configure Path B (selected columns)
* **Open-ended data to analyze** — search and select one or more text columns.
* **Categorical data to compare by** — *auto-detected* here ("AI will auto-identify this for you"), so you don't pick segments manually.
* **(Optional) Name/ID column** — for quote attribution.
Click **"Save & Next"**, then **generate themes** (AI or your own). With multiple columns you'll choose a [codebook](/ailyze-docs/reference/glossary.md#codebook) mode:
* **Separate codebook per column** — each column gets its own themes.
* **Single merged codebook** — columns share one set of themes.
Edit the proposed themes on **"Configure Themes and Submit"** (tabs: **Type Themes**, **Paste Themes**, **Use Previous**), then click **"Create Project and Start Analysis"**.
## Step 5: Check cost and sampling (both paths)
If your selected text exceeds the free word limit (about 90,000 words), Evidano offers to analyze a **random sample** instead of the full data, and shows the charge (about **USD 1.50 per 10,000 words**) before you submit. You confirm any charge in a dialog.
{% hint style="info" %}
**Free vs Pro:** As with documents, Free accounts are limited to **1 theme and 1 question**; Pro unlocks unlimited analysis, sharing, and codebook editing. See [Plans, Limits & Credits](/ailyze-docs/reference/plans-limits-and-credits.md).
{% endhint %}
## Step 6: Read your results
The overall survey dashboard (Path A) groups columns into **Text / Numerical / Categorical / Segment / Respondent ID**. Each column is an accordion with:
* **Visualization** — a chart with a **Segment** dropdown, a **"Segments on y-axis"** option, and **Download CSV / PNG**.
* **Analysis** — an AI narrative, with **"View More Analysis"** opening that column's deep project.
### The per-column thematic project
The deep view for a single open-ended question:
* **Codebook** and **Synthesis**
* **Frequency Bar Chart (Themes)** and **(Sub-themes)** — with segment splitting
* **Hierarchy Graph** and [**Co-occurrence Network**](/ailyze-docs/reference/glossary.md#co-occurrence-network)
* **Word Frequency Visualizer**
* **Data Coded with AI Themes & Sub-themes** — a table with tabs: *AI Labels as List*, *AI Labels as Checklist (with code justifications)*, *Theme & Sub-theme Frequencies*
* **Elaboration of Themes & Sub-themes** — per-theme cards with quotes you can manage
See [How to read your results](/ailyze-docs/analyze-data/how-to-read-your-results.md) for definitions of every section and chart.
## Step 7: Do more with your results
From either results page's **Action** bar:
* **"Chat to generate report or chart"** — query the data and build custom charts. See [Chat with your data](/ailyze-docs/analyze-data/chat-with-your-data.md).
* **Download as DOCX / CSV**, **Share as Webpage** *(Pro)*.
* **Edit Codebook** and **Calculate AI Accuracy** *(Pro)* — see [Build a codebook](/ailyze-docs/analyze-data/build-a-codebook.md).
* In Theme Elaboration: view a quote's full row, delete a quote, or **find similar quotes** to refine coding.
## A realistic example
> **Scenario:** You collected **2,000 NPS (a customer-loyalty score) survey responses** with a score, a reason field, and columns for plan and region. Use **Path A**, drag **plan** and **region** into **Segments**, and let Evidano theme the reason field. You get a dashboard showing the score distribution and category breakdowns by plan and region, plus a deep thematic project on the reasons — then open **Chat** and ask, *"What drives detractors on the Basic plan?"*
## Next steps
* [Analyze customer feedback](/ailyze-docs/common-research-workflows/analyze-customer-feedback.md) — a tailored path for support and NPS data.
* [Compare groups](/ailyze-docs/analyze-data/compare-groups-segments.md) — set up segment comparisons.
* [How to read your results](/ailyze-docs/analyze-data/how-to-read-your-results.md) — a full tour of every section and chart.
* [Survey research best practices](/ailyze-docs/methods-and-best-practices/survey-research-best-practices.md) — tips for cleaner survey analysis.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://ailyze.gitbook.io/ailyze-docs/common-research-workflows/analyze-open-ended-survey-responses.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.