Report: Capture > Traffic Capture: Search default channel group
Dimension: session campaign
Secondary dimension: date
Filter: Source medium contains “newsletter”
Andy passes the report to ChatGPT and gives the following prompt:
“Draw two diagrams. One shows correlations per month. One shows correlations by day of the week. Normalize the data.”
The monthly correlation chart shows a strong performance in the first few months of the year, a decline through October, and a rise in November and December to early year levels. In the weekday chart, Thursday is the clear winner and Saturday is the clear loser.
The next prompt requires sophisticated analysis:
“Create and display a one-year calendar for this newsletter. Schedule it every two weeks and select dates for optimal performance. Write draft headlines for each and select topics for optimal performance.”
ChatGPT’s suggestions include:
Optimal topics: content marketing, SEO
Start date: Next Friday
Frequency: Every other Friday
Of course, you don’t have to follow ChatGPT’s suggestions exactly. However, it fascinates me that these suggestions can be generated based on the data Andy provided.
Complementing and expanding analytics and AI
I was familiar with Google’s Universal Analytics, but I’m a complete newbie to how to connect GA4 reports with generative AI tools. Andy offers a nice way for non-experts:
Build your go-to reports in GA4.
Export the data to CSV files.
Share the files with a generative AI tool like ChatGPT.
Ask the tool to analyze the data and provide recommendations.
With this process, you can learn how to optimize existing content to improve rankings, convert more visitors, and create content calendars that highlight the most effective headlines, topics, frequency, and distribution days.
I’ll now hand the matter over to you and ask: What will happen? You What can you ask of generative AI for your marketing initiatives?
Let me know on social media using the tag #CMWorld.
All tools mentioned in this article were suggested by the author. If you would like to suggest a tool, share the article on social media with a comment.
Register to attend Content Marketing World in San Diego. Use code BLOG100 to save $100. Can’t attend in person this year? Check out the digital pass for access to on-demand session recordings of the live event through the end of the year.
HANDPICKED RELATED CONTENT:
Cover image by Joseph Kalinowski/Content Marketing Institute
“Based on this data, what type of campaigns should be sent more often?”
“What types of campaigns should be abandoned?”
“Suggest changes that would improve the efficiency of this email program.”
“Based on this data, which five possible subject lines would have the highest website conversion rates?”
Campaign timing analysis (dates, days and seasonality)
In his 20+ years of web analytics experience, Andy has never created a report that used newsletter date as a secondary dimension. However, generative AI makes it possible to find patterns in time-related data.
First, Andy creates a GA4 report showing traffic capture from his newsletter, sorted by date:
Report: Capture > Traffic Capture: Search default channel group
Dimension: session campaign
Secondary dimension: date
Filter: Source medium contains “newsletter”
Andy passes the report to ChatGPT and gives the following prompt:
“Draw two diagrams. One shows correlations per month. One shows correlations by day of the week. Normalize the data.”
The monthly correlation chart shows a strong performance in the first few months of the year, a decline through October, and a rise in November and December to early year levels. In the weekday chart, Thursday is the clear winner and Saturday is the clear loser.
The next prompt requires sophisticated analysis:
“Create and display a one-year calendar for this newsletter. Schedule it every two weeks and select dates for optimal performance. Write draft headlines for each and select topics for optimal performance.”
ChatGPT’s suggestions include:
Optimal topics: content marketing, SEO
Start date: Next Friday
Frequency: Every other Friday
Of course, you don’t have to follow ChatGPT’s suggestions exactly. However, it fascinates me that these suggestions can be generated based on the data Andy provided.
Complementing and expanding analytics and AI
I was familiar with Google’s Universal Analytics, but I’m a complete newbie to how to connect GA4 reports with generative AI tools. Andy offers a nice way for non-experts:
Build your go-to reports in GA4.
Export the data to CSV files.
Share the files with a generative AI tool like ChatGPT.
Ask the tool to analyze the data and provide recommendations.
With this process, you can learn how to optimize existing content to improve rankings, convert more visitors, and create content calendars that highlight the most effective headlines, topics, frequency, and distribution days.
I’ll now hand the matter over to you and ask: What will happen? You What can you ask of generative AI for your marketing initiatives?
Let me know on social media using the tag #CMWorld.
All tools mentioned in this article were suggested by the author. If you would like to suggest a tool, share the article on social media with a comment.
Register to attend Content Marketing World in San Diego. Use code BLOG100 to save $100. Can’t attend in person this year? Check out the digital pass for access to on-demand session recordings of the live event through the end of the year.
HANDPICKED RELATED CONTENT:
Cover image by Joseph Kalinowski/Content Marketing Institute
Focus on high engagement topics (e.g. analytics, content marketing, email marketing).
Re-evaluate SEO campaigns.
Each high-level suggestion contains supporting details and leads to additional prompts from Andy, including:
“Based on this data, what type of campaigns should be sent more often?”
“What types of campaigns should be abandoned?”
“Suggest changes that would improve the efficiency of this email program.”
“Based on this data, which five possible subject lines would have the highest website conversion rates?”
Campaign timing analysis (dates, days and seasonality)
In his 20+ years of web analytics experience, Andy has never created a report that used newsletter date as a secondary dimension. However, generative AI makes it possible to find patterns in time-related data.
First, Andy creates a GA4 report showing traffic capture from his newsletter, sorted by date:
Report: Capture > Traffic Capture: Search default channel group
Dimension: session campaign
Secondary dimension: date
Filter: Source medium contains “newsletter”
Andy passes the report to ChatGPT and gives the following prompt:
“Draw two diagrams. One shows correlations per month. One shows correlations by day of the week. Normalize the data.”
The monthly correlation chart shows a strong performance in the first few months of the year, a decline through October, and a rise in November and December to early year levels. In the weekday chart, Thursday is the clear winner and Saturday is the clear loser.
The next prompt requires sophisticated analysis:
“Create and display a one-year calendar for this newsletter. Schedule it every two weeks and select dates for optimal performance. Write draft headlines for each and select topics for optimal performance.”
ChatGPT’s suggestions include:
Optimal topics: content marketing, SEO
Start date: Next Friday
Frequency: Every other Friday
Of course, you don’t have to follow ChatGPT’s suggestions exactly. However, it fascinates me that these suggestions can be generated based on the data Andy provided.
Complementing and expanding analytics and AI
I was familiar with Google’s Universal Analytics, but I’m a complete newbie to how to connect GA4 reports with generative AI tools. Andy offers a nice way for non-experts:
Build your go-to reports in GA4.
Export the data to CSV files.
Share the files with a generative AI tool like ChatGPT.
Ask the tool to analyze the data and provide recommendations.
With this process, you can learn how to optimize existing content to improve rankings, convert more visitors, and create content calendars that highlight the most effective headlines, topics, frequency, and distribution days.
I’ll now hand the matter over to you and ask: What will happen? You What can you ask of generative AI for your marketing initiatives?
Let me know on social media using the tag #CMWorld.
All tools mentioned in this article were suggested by the author. If you would like to suggest a tool, share the article on social media with a comment.
Register to attend Content Marketing World in San Diego. Use code BLOG100 to save $100. Can’t attend in person this year? Check out the digital pass for access to on-demand session recordings of the live event through the end of the year.
HANDPICKED RELATED CONTENT:
Cover image by Joseph Kalinowski/Content Marketing Institute
Engagement with Analytics: Analytics-related campaigns have the highest engagement rate (49.79%) and the longest average engagement time (81.51 seconds). This suggests that subscribers have a strong interest in analytics topics and spend more time engaging with such content.
Content Marketing Effectiveness: While “Content Marketing” has one of the higher open rates (20%), the interaction time is relatively short (35.48 seconds). This could indicate that while the topic initially sparks interest, the content may not engage users for long.
The lower SEO commitment: Campaigns related to “SEO” have one of the lowest engagement rates and shortest engagement times. It might be worth rethinking the content or presentation style of these campaigns to increase engagement.
Advanced Email Marketing Engagement: Despite an average open rate, “email marketing” topics retain users for longer (63.94 seconds), indicating the depth or relevance of the content to the audience.
Andy asks ChatGPT to suggest adjustments to his email marketing program based on the data provided. General suggestions include:
Focus on high engagement topics (e.g. analytics, content marketing, email marketing).
Re-evaluate SEO campaigns.
Each high-level suggestion contains supporting details and leads to additional prompts from Andy, including:
“Based on this data, what type of campaigns should be sent more often?”
“What types of campaigns should be abandoned?”
“Suggest changes that would improve the efficiency of this email program.”
“Based on this data, which five possible subject lines would have the highest website conversion rates?”
Campaign timing analysis (dates, days and seasonality)
In his 20+ years of web analytics experience, Andy has never created a report that used newsletter date as a secondary dimension. However, generative AI makes it possible to find patterns in time-related data.
First, Andy creates a GA4 report showing traffic capture from his newsletter, sorted by date:
Report: Capture > Traffic Capture: Search default channel group
Dimension: session campaign
Secondary dimension: date
Filter: Source medium contains “newsletter”
Andy passes the report to ChatGPT and gives the following prompt:
“Draw two diagrams. One shows correlations per month. One shows correlations by day of the week. Normalize the data.”
The monthly correlation chart shows a strong performance in the first few months of the year, a decline through October, and a rise in November and December to early year levels. In the weekday chart, Thursday is the clear winner and Saturday is the clear loser.
The next prompt requires sophisticated analysis:
“Create and display a one-year calendar for this newsletter. Schedule it every two weeks and select dates for optimal performance. Write draft headlines for each and select topics for optimal performance.”
ChatGPT’s suggestions include:
Optimal topics: content marketing, SEO
Start date: Next Friday
Frequency: Every other Friday
Of course, you don’t have to follow ChatGPT’s suggestions exactly. However, it fascinates me that these suggestions can be generated based on the data Andy provided.
Complementing and expanding analytics and AI
I was familiar with Google’s Universal Analytics, but I’m a complete newbie to how to connect GA4 reports with generative AI tools. Andy offers a nice way for non-experts:
Build your go-to reports in GA4.
Export the data to CSV files.
Share the files with a generative AI tool like ChatGPT.
Ask the tool to analyze the data and provide recommendations.
With this process, you can learn how to optimize existing content to improve rankings, convert more visitors, and create content calendars that highlight the most effective headlines, topics, frequency, and distribution days.
I’ll now hand the matter over to you and ask: What will happen? You What can you ask of generative AI for your marketing initiatives?
Let me know on social media using the tag #CMWorld.
All tools mentioned in this article were suggested by the author. If you would like to suggest a tool, share the article on social media with a comment.
Register to attend Content Marketing World in San Diego. Use code BLOG100 to save $100. Can’t attend in person this year? Check out the digital pass for access to on-demand session recordings of the live event through the end of the year.
HANDPICKED RELATED CONTENT:
Cover image by Joseph Kalinowski/Content Marketing Institute
You have been using the GA4 version of Google Analytics for at least a year, if not two to three. You’ve probably also tested the potential of ChatGPT and similar generative AI tools.
But have you combined the power of both?
This is where Andy Crestodina comes into play. The co-founder and CMO of Orbit Media Studios discussed the possibilities in his Marketing Analytics and Data Science (MADS) Conference Presentation, How to Audit Your Content with GA4: A Data-Driven Approach to SEO and Lead Generation.
In this article, he’ll show you step-by-step how to create GA4 reports and get ChatGPT to detect rising and falling search traffic, improve content rankings, and send more effective newsletters.
What content has rising and falling search traffic?
To see traffic from organic search:
Go to the “Engagement” section in the left column.
From the drop-down menu, click the Pages and Screens: Page Title and Screen Class report.
Then click “Add Filter” to view organic traffic.
To create the filter:
Go to the “Include” drop-down menu in the right column.
Select session medium.
Under Dimension Values, select Organic.
Click “Add Comparison” at the top of the page. Select the period, e.g. B. the last seven days or the last 28 days. Scroll down to turn on the Compare toggle.
Andy says that GA4’s date comparison feature is better than the old Universal Analytics because its comparison matches the days of the week between the two time periods.
The resulting report identifies rising and falling search traffic, as shown in this report:
In the report above, the URL – /blog/how-to-write-testimonials-examples – saw a 43.43% decrease in views when comparing January 7 to February 3, 2023 with December 10, 2022 to March 3 . January 2023 compares. 6, 2023. But the URL – /blog/website-navigation – saw a 42.86% increase in search traffic during the same period.
Once you’ve identified content that’s seeing declining search traffic, consider improving it with these ideas:
What phrases does this article rank for?
Knowing the phrases an article ranks for can help you better understand why people are finding the page. It also helps determine how to optimize additional phrases to drive more organic search traffic to them.
For this purpose, Andy enlists the help of ChatGPT. However, the first step is to create a report through Google Search Console:
Search type: Web
Date: (a time frame) (In this example, Andy selected the last three months.)
Search query: -orbit (i.e. to exclude brand queries for Andy’s agency Orbit Media)
Page: (the page URL)
Click “Export” in the top right to generate a CSV file with the data.
Insert the CSV file into ChatGPT. Andy used ChatGPT Plus ($20 per month) as it supports data analysis and file uploads. He begins with this request:
“I provide you with data from Google Search Console that shows the search performance of a URL. Can you analyze?”
ChatGPT responds with the five columns of data and suggested areas that could be analyzed (e.g. queries that generate the most clicks).
Since each ranking page also ranks for a number of other things, he consolidates the list with this prompt:
“You are an SEO expert who is well versed in keyword analysis. Merge the rows with similar queries into single rows with a single, representative marketing keyword. For each row, combine the impressions and clicks data and average the CTR and average position data. Provide a link to download.”
Every time you ask AI to manipulate data, you are asking it to provide a link to download the data so that you can confirm that it has processed the data properly. In this case, Andy thinks ChatGPT’s data looks good.
The chart contains 19 rows of search queries related to what should be on a website’s homepage, as well as total clicks, impressions, CTR, and position.
With data about which phrases the page ranks for, Andy inserts the content into ChatGPT and issues the following prompt:
“Here is the page with the data you just analyzed. Evaluate the keyword usage and frequency of this content based on the keywords in the data set.”
ChatGPT responds with a series of steps it will perform, including text preprocessing and keyword extraction:
Text preprocessing: We clean the website to prepare it for analysis.
Keyphrase extraction: We identify the key phrases that appear in the content.
Frequency counting: We count how often each key phrase appears in the content.
Evaluation: Finally, we evaluate the use of keywords based on their frequency in the content and their importance in Google Search Console aggregated data.
Andy refines the request to let ChatGPT refine its recommendations (bold emphasis by Andy):
“Suggest changes to this page that will rank higher by better clarifying its relevance to the key phrases in the dataset. Focus on recommendations for including the phrases that are not used on the page but appear in the record. Make suggestions about this Improve content flow and clarityand keyphrase relevance. Highlight the recommended changes.”
What content changes can improve rankings?
I find the results pretty amazing. Some of the recommended changes generated by ChatGPT:
introduction
Current: Social media streams are crowded, fast-paced and very competitive. As social networks decline in organic reach, it becomes harder to be visible and even harder to attract attention.
Suggested Edit: Navigating crowded and competitive environments Social media video landscape can be daunting. With platforms like Facebook and Instagram limiting organic reach, the challenge is to increase your reach DIY social media videos visible is bigger than ever.
Second Section: Winning the Algorithm
Current: Social media videos are so captivating that networks are pushing them to the top of social streams. Facebook, Instagram and LinkedIn all want us to do more in this all-powerful format. It’s winning in the algorithms and it’s gaining attention.
Suggested edit: The power of Creating engaging social media videos is so compelling that platforms like Facebook, Instagram and LinkedIn give them preferential treatment. Therefore, learn how to create compelling social media video content is crucial – it wins both in algorithms and in capturing audience attention.
Third Section: Tools and Equipment
Current: Your laptop has a camera and a microphone, but you can do better. With a little more effort you will get a high quality video and much better results.
Suggested Edit: Even if your laptop’s built-in camera and microphone are enough to get you started, it’s worth investing in specialized equipment Video equipment for social media marketing can significantly increase the quality and engagement of your company DIY social media videos.
Which articles convert email subscribers best?
Over the last 18 years, Andy has written over 575 articles on topics ranging from influencer marketing to web analytics to email marketing. Some articles perform amazingly while others get no traffic. Similarly, some articles get people to subscribe to Orbit’s email list, while others don’t generate subscribers.
“Knowing this difference will help you know exactly what to do on social media. You know what to promote and what works well,” says Andy.
In the past, he used Excel spreadsheets to analyze each article on his website. Nowadays he uses ChatGPT.
First he collects the data from GA4. In the Engagement section, he selects the Page and Screens: Page Path + Query String report. To customize it, he clicks the pencil icon in the top right and adds these metrics:
meetings
user
Conversions
TIP: If your metric doesn’t appear immediately, enter its name and select it when it appears.
Since Andy only wanted blogs in his dataset, he clicked “Add Filter” in the top left and created the filter with these attributes:
Dimension: Page path and screen class
Match type: contains
Value: Blog
From here, click on the export icon in the top right (i.e. there are two icons to the left of the pencil icon) and select “Download CSV”.
Next, Andy creates a second CSV file by changing “Value: blog” to “Value: /blog-newsletter-thank-you-page” to capture his email signup thank you page data:
He clicks the + button to the left of the report columns to select a secondary dimension of Page Reference. The resulting report shows the pages users read before subscribing to Orbit’s email list. He exports this data as CSV.
Andy cleans up this file by deleting the nine lines of metadata at the top so ChatGPT doesn’t get confused during analysis.
The two files are fed into ChatGPT to confirm that they can be analyzed. Next, Andy asks ChatGPT to perform the equivalent of an Excel VLOOKUP to allow users to find things in a table or range, row by row. He uses this prompt:
“Map the data from the two files together into one file, like you would with vlookup, so that each line is a URL and the sessions and conversions are shown for each.”
He asks ChatGPT to provide a file for download. ChatGPT generates 17 lines of URLs accompanied by sessions (traffic), users (traffic), conversions, sessions, users (converted) and conversions (newsletter):
Andy then asks ChatGPT to draw a bar chart showing the conversion rate for each blog post.
ChatGPT responds by calculating the conversion rate for each blog post and visualizing a bar chart showing the top 20 blog posts by conversion rate.
NOTE: Conversion rate data is only available because ChatGPT has divided the conversion data (numerator) by session traffic (denominator).
Next Steps
To highlight the articles that drive the most email conversions, Andy suggests the following:
Promote the article(s) in your email signature
Showcase them on your homepage
Include them in a social media marketing rotation
Linking in presentations
Linking to them from highly trafficked sites
Which email campaigns perform best?
You can also use the GA4-ChatGPT combination to understand which email campaigns are performing the best. Here’s how Andy does it:
Export GA4 data showing traffic to pages based on UTM codes related to email campaigns.
Export data from Orbit’s email marketing platform (ActiveCampaign).
Ask ChatGPT to merge the two datasets, analyze them and make recommendations
To collect the GA4 data, Andy uses the Traffic Capture report, which can be found under “Collection” in the left navigation bar. He clicks the pencil in the top right to adjust it and selects the following metrics before clicking the Apply button:
meetings
Engagement rate
Average interaction time per session
Conversions
Session conversion rate
Next, he clicks Add Filter, selects the Session Medium dimension, and then selects the Email value.
Andy changes the primary dimension to Session Campaign. The resulting report contains one row for each email campaign (i.e. traffic statistics based on the utm_campaign parameter). Andy exports this data as a CSV file.
Next, Andy exports a data file from ActiveCampaign that contains the following:
Campaign name
Number of shipments
Number of openings
Number of clicks
Number of unsubscribes
Number of bounces
Open rate
Click rate
Deregistration date
Bounce rate
Andy uploads each file individually to ChatGPT and confirms that each file can be processed. He then asks ChatGPT to merge the records:
“These two data sets show the performance of the same campaigns from both email service provider (active campaign) and website behavior (Google Analytics). I want to see the performance of each campaign in both datasets. Merge the Google Analytics data with the ActiveCampaign data, combine “Session Campaign” and “Campaign Name” into one column, and use the names and dates to deduce which campaigns were the same. Provide a link to download.”
Once ChatGPT merges the data sets, Andy confirms that the data looks good and puts ChatGPT up and running.
The basic prompt is:
“You are an experienced digital strategist and email marketing expert. What insights can you gain from the combined data set?”
Moonshot prompts include:
“What can you tell me about newsletter campaigns?”
“What insights can you gain from this data?”
“Create a chart using an unusual visualization method that shows unexpected insights from the data in this dataset.”
“How would Leonardo da Vinci visualize this data? Show your thinking.”
Next, Andy asks ChatGPT to categorize the newsletter campaigns and provide insight into the metrics for each category. It provides these strategic insights:
Engagement with Analytics: Analytics-related campaigns have the highest engagement rate (49.79%) and the longest average engagement time (81.51 seconds). This suggests that subscribers have a strong interest in analytics topics and spend more time engaging with such content.
Content Marketing Effectiveness: While “Content Marketing” has one of the higher open rates (20%), the interaction time is relatively short (35.48 seconds). This could indicate that while the topic initially sparks interest, the content may not engage users for long.
The lower SEO commitment: Campaigns related to “SEO” have one of the lowest engagement rates and shortest engagement times. It might be worth rethinking the content or presentation style of these campaigns to increase engagement.
Advanced Email Marketing Engagement: Despite an average open rate, “email marketing” topics retain users for longer (63.94 seconds), indicating the depth or relevance of the content to the audience.
Andy asks ChatGPT to suggest adjustments to his email marketing program based on the data provided. General suggestions include:
Focus on high engagement topics (e.g. analytics, content marketing, email marketing).
Re-evaluate SEO campaigns.
Each high-level suggestion contains supporting details and leads to additional prompts from Andy, including:
“Based on this data, what type of campaigns should be sent more often?”
“What types of campaigns should be abandoned?”
“Suggest changes that would improve the efficiency of this email program.”
“Based on this data, which five possible subject lines would have the highest website conversion rates?”
Campaign timing analysis (dates, days and seasonality)
In his 20+ years of web analytics experience, Andy has never created a report that used newsletter date as a secondary dimension. However, generative AI makes it possible to find patterns in time-related data.
First, Andy creates a GA4 report showing traffic capture from his newsletter, sorted by date:
Report: Capture > Traffic Capture: Search default channel group
Dimension: session campaign
Secondary dimension: date
Filter: Source medium contains “newsletter”
Andy passes the report to ChatGPT and gives the following prompt:
“Draw two diagrams. One shows correlations per month. One shows correlations by day of the week. Normalize the data.”
The monthly correlation chart shows a strong performance in the first few months of the year, a decline through October, and a rise in November and December to early year levels. In the weekday chart, Thursday is the clear winner and Saturday is the clear loser.
The next prompt requires sophisticated analysis:
“Create and display a one-year calendar for this newsletter. Schedule it every two weeks and select dates for optimal performance. Write draft headlines for each and select topics for optimal performance.”
ChatGPT’s suggestions include:
Optimal topics: content marketing, SEO
Start date: Next Friday
Frequency: Every other Friday
Of course, you don’t have to follow ChatGPT’s suggestions exactly. However, it fascinates me that these suggestions can be generated based on the data Andy provided.
Complementing and expanding analytics and AI
I was familiar with Google’s Universal Analytics, but I’m a complete newbie to how to connect GA4 reports with generative AI tools. Andy offers a nice way for non-experts:
Build your go-to reports in GA4.
Export the data to CSV files.
Share the files with a generative AI tool like ChatGPT.
Ask the tool to analyze the data and provide recommendations.
With this process, you can learn how to optimize existing content to improve rankings, convert more visitors, and create content calendars that highlight the most effective headlines, topics, frequency, and distribution days.
I’ll now hand the matter over to you and ask: What will happen? You What can you ask of generative AI for your marketing initiatives?
Let me know on social media using the tag #CMWorld.
All tools mentioned in this article were suggested by the author. If you would like to suggest a tool, share the article on social media with a comment.
Register to attend Content Marketing World in San Diego. Use code BLOG100 to save $100. Can’t attend in person this year? Check out the digital pass for access to on-demand session recordings of the live event through the end of the year.
HANDPICKED RELATED CONTENT:
Cover image by Joseph Kalinowski/Content Marketing Institute
