Create your survey

Create your survey

Create your survey

How to use AI to analyze responses from ecommerce shopper survey about returns process

Adam Sabla - Image Avatar

Adam Sabla

·

Aug 28, 2025

Create your survey

This article will give you tips on how to analyze responses from an ecommerce shopper survey about the returns process using the latest AI survey analysis tools so you can understand what your shoppers really think and act on their feedback right away.

Choosing the right tools for analyzing ecommerce shopper survey data

The best approach and tooling for analyzing your returns process survey depends on what kind of data you have in your responses. It’s key to match your method to your survey’s structure:

  • Quantitative data: Numbers are your friend here — for example, tallying how many respondents picked a certain choice or gave a particular Net Promoter Score. You can quickly get these counts using standard tools like Excel or Google Sheets for survey question breakdowns, and see patterns fast.

  • Qualitative data: When you’re dealing with open-ended answers, detailed stories, or multi-layered follow-up responses, it’s practically impossible (and very slow) to read them all yourself. That’s where AI comes in, because these responses deserve to be explored by tools made for extracting meaning at scale.

There are two main approaches for tooling when dealing with qualitative responses:

ChatGPT or similar GPT tool for AI analysis

You can copy and paste exported survey data into ChatGPT and chat about the results, asking about themes or summarizing what your ecommerce shoppers said about returns.

This method isn't ideal, especially for bigger surveys — preparation and context are limited. Formatting data for GPT, pasting everything, and dealing with context limits can quickly become tedious, and you may need to guide the analysis step by step.

All-in-one tool like Specific

Specific is an AI platform built specifically for conversational survey analysis.

  • Data collection is smarter: When you build your ecommerce shopper survey in Specific, it automatically asks follow-up questions, making the raw data richer and more actionable. Learn more about automatic AI follow-ups.

  • AI-powered analysis is instant: As soon as the survey responses arrive, the platform summarizes answers, finds key themes, and organizes insights — you don’t need any spreadsheets or manual sorting.

  • Conversational understanding: You can chat with AI about your survey responses and ask for custom summaries, almost like ChatGPT but optimized for survey data. On top of that, you can manage what’s sent to AI contextually, keeping the analysis focused and relevant.

If you want to create your own conversational AI survey for ecommerce shoppers about the returns process, you can get started with a ready-made generator and analyze the results in one place.

Useful prompts that you can use to analyze ecommerce shopper survey responses about the returns process

Smart prompting is the best way to turn piles of qualitative data into real understanding. Here’s how to get the most out of AI analysis (no matter if you use ChatGPT, another GPT, or a purpose-built tool like Specific):

Prompt for core ideas: This works wonders for extracting the key topics or recurring themes in large returns process data sets. Try this:

Your task is to extract core ideas in bold (4-5 words per core idea) + up to 2 sentence long explainer.

Output requirements:

- Avoid unnecessary details

- Specify how many people mentioned specific core idea (use numbers, not words), most mentioned on top

- no suggestions

- no indications

Example output:

1. **Core idea text:** explainer text

2. **Core idea text:** explainer text

3. **Core idea text:** explainer text

Extra context yields better results. The more details you give the AI about your survey and your goals, the sharper the analysis. For example:

Here's the context: We surveyed 250 ecommerce shoppers after they finished a return or refund process on our apparel site. The goal is to uncover pain points and opportunities to improve the post-purchase experience, especially related to returns speed, communication, and packaging.

Once you get the initial set of themes or ideas, you can probe deeper:

Prompt for digging deeper: “Tell me more about [e.g. return shipping pain points]” — this gets the AI to zoom in with more detail or examples from your data.

Prompt for specific topic: “Did anyone talk about packaging?” — for instance, to quickly validate a suspected issue or see if your returns experience stands out. Add “Include quotes” if you want verbatim shopper feedback.

Prompt for personas: To split your audience into types: “Based on the survey responses, identify and describe a list of distinct personas—similar to how 'personas' are used in product management. For each persona, summarize their key characteristics, motivations, goals, and any relevant quotes or patterns observed in the conversations.”

Prompt for pain points and challenges: “Analyze the survey responses and list the most common pain points, frustrations, or challenges mentioned. Summarize each, and note any patterns or frequency of occurrence.”

Prompt for sentiment analysis: “Assess the overall sentiment expressed in the survey responses (e.g., positive, negative, neutral). Highlight key phrases or feedback that contribute to each sentiment category.”

All of these prompts can be used in Specific’s AI-powered response analysis or dropped directly into ChatGPT if you’re doing things manually.

How Specific analyzes qualitative survey data by question type

Specific is designed to use the structure of your ecommerce survey to organize results for you — and the analysis varies by question type:

  • Open-ended questions: You get a clear summary of all responses and all associated follow-up answers about the returns process. This is where deep experiences, suggestions, or pain points stand out — critical since returns in ecommerce can impact profits (average ecommerce return rates rose to 16.9% in 2024, totaling $743 billion in returned sales [1]).

  • Choices with follow-ups: Each answer (such as “what was your returns method?”) gets its own summary covering all feedback and experiences related to that choice. You can see, for example, how shoppers who chose in-store return differed from those who mailed back items.

  • NPS questions: Returns process NPS questions are broken down by promoter, passive, and detractor categories, so you can immediately compare what’s driving loyalty versus dissatisfaction in each group. High return costs hurt — returns can cost between 20% and 65% of the original cost of goods sold [4] — so spotting root causes is essential.

If you use ChatGPT, these breakdowns are possible, but you’ll have to do more prep work and document management to get the same clarity.

How to deal with AI context size limits in survey analysis

Even the best AI models have limits — there’s only so much data you can paste into a single prompt. For ecommerce shopper surveys that get dozens or hundreds of responses about returns, you’ll probably run into a context size wall. To handle this, you have two robust options (both built into Specific):

  • Filtering: Narrow down the analysis by filtering conversations where shoppers replied to particular returns process questions or selected specific choices. This lets you ask AI to only analyze, for example, people who returned an item in the last 30 days, or those who used free shipping.

  • Cropping: Focus AI only on selected survey questions. If your survey had open-ended “pain point” questions and specific “speed of return” scale questions, you can crop the data for AI analysis just to those topics, getting around length limits and producing more focused insights.

Specific streamlines this for direct use in the analysis chat UI, but you could also replicate it manually by sorting and segmenting exported data for smaller AI prompts in ChatGPT.

Collaborative features for analyzing ecommerce shopper survey responses

It’s easy to get lost in the weeds when a team is trying to analyze dozens of shopper responses about the ecommerce returns process, especially when opinions, follow-up questions, and action items start multiplying.

Analysis by conversation with AI: On Specific, you and your team can analyze feedback simply by chatting with the AI about results; you don’t need to export or import anything, and the chat stays contextualized.

Parallel, filterable chats: Team members can open multiple, independent analysis chats focused on different areas (like speed of return, packaging complaints, or fraud detection). Each chat can have custom filters and it’s easy to see who owns or started each thread.

Clear attribution for teamwork: Collaboration gets even cleaner with avatars showing the sender for every question and response in the AI chat — so you always know who requested specific insights into returns pain points, and who asked follow-up questions about, say, free shipping or repackaging.

These features are tailored to help teams work faster and with fewer misunderstandings, so improvements to the returns process — which has clear business impact since 92% of consumers are more likely to buy again if returns are easy [6] — can be made with confidence and buy-in from everyone involved.

Create your ecommerce shopper survey about returns process now

Start getting answers to the questions that actually matter for your business. Build a survey in minutes, capture actionable shopper feedback on your returns process, and use AI-powered analysis to make data-driven improvements with zero manual work.

Create your survey

Try it out. It's fun!

Sources

  1. FT.com. In 2024, the average return rate for e-commerce purchases was 16.9%, with returns totaling $743 billion.

  2. CapitalOneShopping.com. Approximately 63% of consumers purchase products in multiple sizes and return items that don’t fit.

  3. Zipdo.co. Apparel purchases online have a return rate as high as 40%.

  4. WorldMetrics.org. The cost of processing a return can range from 20% to 65% of the original cost of goods sold.

  5. AmraAndElma.com. 67% of shoppers check the return policy before making a purchase.

  6. WorldMetrics.org. 92% of consumers are more likely to buy again if the return process is easy.

Adam Sabla - Image Avatar

Adam Sabla

Adam Sabla is an entrepreneur with experience building startups that serve over 1M customers, including Disney, Netflix, and BBC, with a strong passion for automation.

Adam Sabla

Adam Sabla is an entrepreneur with experience building startups that serve over 1M customers, including Disney, Netflix, and BBC, with a strong passion for automation.

Adam Sabla

Adam Sabla is an entrepreneur with experience building startups that serve over 1M customers, including Disney, Netflix, and BBC, with a strong passion for automation.