Web Analysis

By Michael Rieken / April 19, 2026

To understand how your website is performing, you can use Google Analytics (GA4) to examine key metrics such as user acquisition, engagement, and demographic details. User acquisition shows how many new users your website is getting as well as the sources those users are coming from. It allows you to see which platforms or sources are the most effective for gaining users for your website. Engagement shows which pages are performing best and how users interact with your content. Demographic details allow you to see if you are targeting the geographic regions you intended to reach.

We will also use ChatGPT to analyze the GA4 data.

User acquisition – First user source / medium

We use first user source / medium to show where the new users are coming from. The metrics we focus on in this section are new users, engaged sessions per active user, and average engagement time. New users show how many first-time users are visiting the site. Engaged sessions per active user shows how often users are actively interacting with the site. Average engagement time shows how long users are spending engaged on the website.

Below is an image of the GA4 analytics that shows the user acquisition with these three stated metrics.

After gathering this information, I entered the relevant information into an Excel sheet to make the data more organized and easier to input into ChatGPT.

After organizing the data into Excel, I used ChatGPT to analyze the results. I entered the prompt along with the values for average engagement time.

Prompt used:
When I sorted the average engagement time in descending order in the First user source/medium classification, the following result came out. Please explain.

ChatGPT Result

The table represents user traffic sources and their corresponding average engagement times. Here is an explanation of each:

1. hpanel.hostinger / referral – 2m 47s:
   This source has the highest engagement time, indicating that users coming from this referral are highly engaged and spend the most time interacting with the website content.
2. (direct) / (none) – 4s:
   This represents users who accessed the website directly. Although this source brings the most users, the engagement time is very low, suggesting users are leaving quickly without meaningful interaction.
3. linkedin / referral – 4s:
   Users coming from LinkedIn also show low engagement time, indicating that the content may not fully match user expectations or interest from that platform.

For the next section, I used ChatGPT to analyze the data collected on new users.

Prompt used:
When I sorted the new users in descending order in the First user source/medium classification, the following result came out. Please explain.

ChatGPT Result

The table shows the breakdown of new users by source/medium:

1. (direct) / (none) – 125:
   Most new users come from direct traffic. This suggests strong brand awareness or users accessing the website directly.
2. hpanel.hostinger / referral – 1:
   Only one new user came from this referral source, but earlier data shows this user was highly engaged.
3. linkedin / referral – 1:
   One new user came from LinkedIn, indicating limited reach or effectiveness on that platform.

Analysis:
While direct traffic generates the most users, it has low engagement. Referral traffic, although smaller, provides higher-quality users.

For the last section, I used ChatGPT to analyze engaged sessions per active user.

Prompt used:
When I sorted the engaged sessions per active user in descending order in the First user source/medium classification, the following result came out. Please explain.

ChatGPT Result

1. hpanel.hostinger / referral – 6.00:
   This source has the highest engagement level, meaning users from this referral interact frequently with the site.
2. linkedin / referral – 1.00:
   LinkedIn users show moderate engagement but still lower than referral traffic.
3. (direct) / (none) – 0.10:
   Direct traffic has the lowest engagement, indicating that most users are not interacting deeply with the content.

Analysis and Recommendations:
Referral traffic provides the highest-quality engagement, while direct traffic needs improvement. Improving landing pages and content relevance could increase engagement for direct users.

Engagement – Page title and screens

We use page title and screens to determine which pages are seeing the most engagement. The metrics we focus on in this section are average engagement time, views, and users. Average engagement time shows how long users are spending on each page. Views show how often content is being accessed. Users show how many people are interacting with each page.

Below is an image of the GA4 engagement data.

After collecting this information, I entered the data into Excel.

I then used ChatGPT to analyze the average engagement time.

Prompt used:
When I sorted the average engagement time in descending order in the Page title and screen class classification, the following result came out. Please explain.

ChatGPT Result

1. Homepage – 1m 16s:
   This page has the highest engagement, showing that users spend the most time here.
2. Content creation with AI for REI Coop – 53s:
   This page shows strong engagement, indicating user interest in AI-related content.
3. Same REI page (direct) – 26s:
   Moderate engagement suggests users are somewhat interested.
4. Content creation for North Face – 21s:
   Lower engagement compared to other pages.
5. Customer persona page – 11s:
   Lowest engagement, suggesting limited user interest.

Analysis:
AI-related content performs better than other content, especially when accessed through referral sources.

For the next section, I analyzed views.

Prompt used:
When I sorted the views in descending order in the Page title and screen class classification, the following result came out. Please explain.

ChatGPT Result

All pages show equal views (1 view each), indicating low overall traffic. This suggests that content visibility and promotion need improvement.

For the last section, I analyzed users.

Prompt used:
When I sorted the users in descending order in the Page title and screen class classification, the following result came out. Please explain.

ChatGPT Result

1. Homepage – 5 users:
   This page has the highest number of users, making it the most visited.
2. Customer persona page – 3 users:
   Moderate traffic compared to other pages.
3. Other pages – lower user values:
   These pages have minimal traffic and may need better promotion.

Analysis:
The homepage performs best, while other pages need improved visibility and engagement strategies.

User attribute – Demographic details

We use country and city to see if the website content is reaching the desired audience. The metrics used are active users, engagement rate, average engagement time per active user, and engaged sessions per active user.

Below is an image of the GA4 demographic data.

After collecting the data, I entered it into Excel.

I used ChatGPT to analyze all four metrics together.

Prompt used:
When I sorted the demographic data by city across active users, engagement rate, average engagement time, and engaged sessions per active user, the following result came out. Please explain.

ChatGPT Result

1. Flint Hill:
   Highest engagement rate (17.65%), highest engagement time (6s), and highest engaged sessions (0.18). This indicates the most engaged audience.
2. San Jose:
   Moderate engagement with 10% engagement rate and 0.10 engaged sessions.
3. Not set:
   Some engagement but unclear location data.
4. Des Moines and New York:
   0% engagement and 0 sessions, indicating no interaction from users in these locations.

Conclusion:
Flint Hill is the strongest performing location, while other locations show low engagement and may require better targeting.

Conclusion

This process shows how Google Analytics (GA4) can be used to evaluate website performance and user behavior. By using ChatGPT to analyze the data, it becomes easier to understand what the metrics mean and how they can be used to improve marketing strategies. This allows for better decision-making in content creation, targeting, and overall website optimization.