Instant Insights The Beginners Generative AI Starter Kit 3

Using ChatGPT for Survey Analysis

This content was originally featured in the November 1 2023 newsletter found here: https://www.trustinsights.ai/blog/2023/11/inbox-insights-november-1-2023-chatgpt-survey-analysis-root-cause-analysis/.

Last week we ran our quarterly 1 question survey. We asked, “If you had money left over in your marketing budget this year, what would you spend it on?”

You can still respond to our 1 question survey here: https://www.trustinsights.ai/contact/1-question-survey-from-trust-insights-q4-2023/

We’re seeing budgets cuts across the board. So, our goal was to understand what’s is on the wish list so that we could see how to address it through content and other resources.

Because it’s a simple form, I can export the data into a CSV file. And then it occurred to me. Why should I struggle through analyzing this data when I can ask my pal, KatieGPT to do it for me?!

Ok, we haven’t yet built KatieGPT, so I’ll use ChatGPT instead.

For this exercise, I used GPT4 which allows you to upload data sets for analysis. And like every interaction with ChatGPT, you need a prompt. Mine was super basic:

“You are a market research analyst and you asked your audience “If you had money left over in your marketing budget this year, what would you spend it on?” You are analyzing the data to be easily understood.

Attached are the responses.

This is what you need to answer:

What are the overall themes?

Can you put these responses into some kind of chart?

What was surprising?

What will people primarily spend their budgets on?

Show your work

Provide a download links for any images or charts”

When I saw Andy Crestodina present his session on using GA4 data for SEO a few weeks ago, he did so using ChatGPT. It was really straightforward but incredibly powerful. One of the pro-tips that stood out to me was to ask ChatGPT, “provide a download link”. So simple. So genius. Thanks, Andy!

Here is what ChatGPT told me was in the data:

1. Overall Themes:

– Research and analytics tools

– Data and design improvements

– Marketing and website enhancements

– AI and training

– Marketing strategy and tools

2. Primary Areas for Spending:

– People are primarily interested in spending their leftover marketing budgets on AI and training, followed by marketing strategy and tools.

3. Surprising Insights:

– A significant focus on AI and training indicates that marketers are keen on leveraging AI to enhance their marketing efforts and are willing to invest in training to better understand and utilize AI tools.

It’s interesting that ChatGPT thinks AI education is a suprising insight. I don’t find that surprising at all.

And when we drill down into the themes themselves:

1. Research and Analytics

– Keywords: research, tool, analytics, help, consultant, clients, user, track, streamline, engagement

2. Data and Design

– Keywords: data, figuring, design, bad, cleansing, added, prevent, processes, leverage, thrive

3. Marketing and Website

– Keywords: money, ai, marketing, new, website, meetup.com, asking, left, cms, content

4. AI and Training

– Keywords: ai, training, marketing, video, budget, order, insights, education, id, tools

5. Marketing Strategy and Tools

– Keywords: marketing, tools, ability, great, strategy, new, use, years, year, unified

Ok, this is interesting. I’m starting to see the specific language used within each theme. This is pretty valuable to any marketer.

Because I was curious to see it visualized, I also asked for a a chart and a word cloud. Here’s the word cloud, but I don’t find it to be super helpful:

ChatGPT Word Cloud

All told, this took me 30 minutes. Less time that it’s taking me to write it up. The next question is the best question. So what? What do we do with this information? I know what my answer is, but since we’re on a roll, I asked ChatGPT.

This is where the wheels started to come off.

The suggestions from ChatGPT were fairly generic and uninspired. Many of the suggestions were theoretical and not tactical.

But we were doing so good!

Alright ChatGPT, you’re off the hook for now. Let’s go back to the specific keywords. That starts to fill in our content calendar, our targeting, our topics. We want to mirror the language used by our audience so it resonates with them when they see it.

All told, I think ChatGPT did a pretty good analysis. It’s basic, sure. But it got me what I needed. I have some actionable data that I can start using, all in the same amount of time it takes to get a pizza delivered. Be on the lookout for more content using your feedback!

postsignature]

Leave a Reply

Your email address will not be published. Required fields are marked *

Pin It on Pinterest

Share This