Pillar Pages: Why and How You Should Add Them to Your Content Strategy

In a recent study, we found that our pillar pages are magnets for links, organic traffic, and newsletter subscribers — especially compared to regular blog posts. Here are the results that both types of SEO content generated over the course of a year:

Do these results mean you should ditch your blog strategy in favor of pillar pages? Not exactly.

Here’s the catch: You really can’t have one without the other, and it all comes down to content mapping. I’ll explain exactly what I mean in this article.

What is a pillar page?

A pillar page is a piece of content that comprehensively covers a broad topic. Pillar page — also sometimes referred to as hub and spoke — content weaves together a wide range of relevant subtopics (spokes), organizes them all in one place (hub), and effectively showcases your subject matter expertise for the broad topic.

Pillar page content should be easy to navigate for readers looking to learn — at a high level — about a particular topic, but should also offer relevant resources for them to dive deeper. 

Example of related resources found on a pillar page.

It’s kind of like the choose-your-own-adventure of content marketing.

Topical authority: why it’s important

When it comes to content creation for SEO and digital marketing, you don’t want to create content around any old topic. Instead, you want to reinforce your brand’s topical authority with every new piece of content you create (be it a blog, a pillar page, an eBook, etc.).

Let’s put it this way: If you’re in the business of selling mechanical keyboards, it doesn’t make sense to publish a blog article about the best recipes for a summer BBQ. Unless you’re recommending that your customers grill and eat their mechanical keyboards, which is (highly) unlikely.

Instead, it’s more helpful to your brand — and your audience — if you cover topics related to mechanical keyboards, like:

• What is a mechanical keyboard?

• Mechanical keyboards vs. regular keyboards.

• Custom mechanical keyboards.

• How to transition to a mechanical keyboard.

• Pros and cons of a mechanical keyboard.

By covering as many topics related to mechanical keyboards as possible, you’re building a foundation of informational content that tells search engines: “Hey, I know a lot about mechanical keyboards!”

And the more content you have that starts to rank for important search terms related to mechanical keyboards, the more likely searchers will see you as an authority on the subject. Ideally, they will start coming back to your content when they need to learn more about this specific topic.

Pillar pages + blogs = a match made in content marketing heaven

A well-executed and organized pillar page is one of the best ways to showcase to your audience (and search engines) that you have topical authority in a specific area. Blog posts help you achieve topical authority by allowing you to cover a wide range of relevant subtopics in great detail, and pillar pages organize all of that content into a nice, user-friendly package.

Let’s take a look at this tactic in action.

We built our content marketing guide as a pillar page, which allowed us to cover a slew of subtopics related to the broader topic of content marketing, all in one piece of collateral. 

All of these subtopics are organized into sections on the page, with a hyperlinked table of contents at the top to allow readers to pick and choose exactly what they’d like to learn about:

Then, throughout the page, we offer readers the opportunity to go deeper and learn more about each subtopic by linking to relevant blog content:

What is content mapping?

A pillar page is a great tactic if you’ve got a lot of existing blog content all focused on a particular parent topic. It’s one of our favorite ways at Brafton to repurpose and repromote our blogs.

But you can also create a pillar page with all brand-new content — it’ll just take more research, planning, and production time to complete.

Enter: content mapping.

Content mapping is the process of assessing your target audience, understanding what they are trying to achieve, and helping them along that journey with branded educational and commercial content. Its scope can span the entirety of your content marketing strategy or a single piece of pillar page content.

Why content mapping matters in content marketing

The planning (or content mapping) of a pillar page is just as important as the research done to choose the correct keyword to target for your business.

Pillar pages are kind of like the books of the marketing world. If you were an expert birder, for example, you wouldn’t set out to write a book about bird-watching without doing any research. Especially if you’ve spent a lot of time writing and publishing articles about bird-watching on your blog. You’d want to understand a few things before starting that book, like:

1. Which of my blog posts generated the most interest from new and returning readers? (i.e. pages with the most new and returning visitors, as seen in your web analytics tool).

2. Which blogs kept readers coming back for more? (i.e. pages with the most newsletter subscriptions, or the best newsletter subscription rates).

3. Which blogs did my industry peers find most useful? (i.e. pages with the greatest number of high-quality referring domains and backlinks).

These questions can be answered by looking through your web analytics tools, such as Google Analytics and Moz Pro.

Example of content analysis by top linking domains.

You’d also want to understand what the competition looks like before you spend dozens of hours writing thousands of words to fill a book.

You’d want to answer questions, like:

1. What do my competitors’ books on bird-watching look like? (i.e. the types of bird-watching subtopics the page 1 results cover).

2. What does Google think searchers want to see when they search for bird-watching? (i.e. the types of content that are found on page 1 for your target keyword — and surprise! it might not be books).

3. How long and detailed are my competitors’ books? (i.e. the level of complexity and comprehensiveness of the content ranking on page 1).

These questions can be answered by manually reviewing relevant SERPs and utilizing TF-IDF tools like Clearscope or MarketMuse to understand the breadth of subtopics and types of content ranking on the first page.

Example of manual SERP inspection.

Example of TF-IDF content analysis.

Once you understand which of your content performs best and which content Google and other search engines prefer to rank highly for your target keyword, you can start piecing together a plan for your pillar page.

A note about internal linking

Before we dive into the how-to portion of this piece, we should also acknowledge the importance of internal linking to this whole process.

And I’m not just talking about throwing in a link to a related product/service at the end of the page and calling it a day. The internal linking structure of your pillar page is literally the glue that holds the whole thing together. It helps readers easily navigate to related resources to continue learning from your brand. And it helps search engines understand the relationship between your pillar page content and the additional content you’re highlighting on the page.

But when it comes to internal linking, there is such a thing as too much of a good thing.

Including too many internal links throughout your content can cause a frustrating user experience or look spammy, so use caution and make sure the only internal linking you do on the page is extremely relevant to the parent topic.

If you’re unsure whether or not you’ve got too many internal links on the page, you can run it through Moz’s On-Page Grader tool, which automatically counts the number of links on your page and flags if you’ve got too many.

Tip: Keep in mind that this tool will count ALL links found on the page, including those in your main navigation and footer, so the “Too Many Links” warning could be a false positive.

As Moz explains: Google recommends you don’t go over 100 internal links per page, because it can dilute the SEO value sent from the pillar page to the linked pages, and it can also make it more challenging for users and crawlers to navigate all of the content.

Two data-led ways to map out content for a pillar page

There are a couple of different ways to approach the construction of this type of content, but they each rely on organic search data to lead the way.

1. Planning a pillar page and related resources (all from scratch)

Let’s pretend you don’t have any prior content created about a particular topic. You’re basically starting from scratch. Let’s also assume the topic you’ve selected is both core and commercially valuable to your business, and that your domain realistically has a chance of ranking on page 1 for that keyword.

Let’s say you’re a pet food company and one of your main products is cat dental treats. Once you’ve determined that this is the exact keyword you want to target (“cat dental treats”), it’s time to start your research.

Step 1: Manually inspect SERP to understand searcher intent

First, we’ll start by manually inspecting the first SERP for this keyword, and answering the following questions:

1. What types of content are on the first page of results?

2. Why are people searching for “cat dental treats”?

By answering these two questions in our SERP analysis, we’ll make sure that our plan for creating a pillar page to rank actually makes sense and it’s what searchers want to see on the SERP. We’ll also better understand all the reasons behind why someone might search this keyword (and we can then address those reasons in the content we create).

So let’s answer these questions:

Question 1: What types of content are on the first page of results?

Answer 1: The first SERP includes a variety of product ads, a People Also Ask section, and a selection of organic blogs and product pages.

Types of content found on the SERP for “cat dental treats.”

Question 2: Why are people searching for “cat dental treats”?

Answer 2: From a quick analysis of the SERP, we can deduce that people want to know why and how cat dental treats are important to a cat’s health, and they also want to know which cat dental treats work best. Perhaps most importantly, it’s highly likely that they plan to purchase cat dental treats for their furry companion(s) in the near future.

Step 2: Select related keyword ideas for blog content

Since you don’t just want to create a pillar page for just the primary keyword, you also want to pinpoint a selection of related subtopics to be written as blog content.

For this part of the process, head over to your keyword research tool, plug in your target keyword and (with an eye for topics that you’re well-suited to cover), jot down a list of keywords and phrases.

Here’s our list of potential blog topics:

• Best cat dental treats.

• How do cat dental treats work?

• What to look for in cat dental treats.

• Do cat dental treats work?

• Can cat dental treats replace brushing?

• Vet recommended cat dental treats.

• Grain-free cat dental treats.

Step 3: Choose subtopics to cover in your pillar page content

Next, you’ll want to review the subtopics mentioned in the top ranking results. While this process can be done manually (by clicking into each result on the SERP and jotting down the topics mentioned), a TF-IDF tool like MarketMuse makes this part of the process much quicker:

These TF-IDF tools analyze the top 10-20 results for your target keyword and automatically present the common subtopics mentioned in each piece. This gives you a very good understanding of what you’ll also need to cover in your piece to compete for a top-ranking spot.

Here’s the list of subtopics we’ll want to cover in this pillar page, based on our MarketMuse data:

• Cat dental treats.

• Clean teeth.

• Purina dentalife.

• Feline greenies.

• Fresh breath.

• Natural ingredients.

• Veterinary oral health council.

• Best cat dental treats.

• Artificial flavors.

• Cats dental health.

Step 4: Create your outline and plan content

Now it’s time to connect the dots from your research. The best way to do this is to start by structuring your pillar page outline, and then going back in and filling in the areas where you want to create supporting blog content.

Here’s an example of what the end result might look like:

H1: The Complete Guide to Cat Dental Treats: For a Fresh-Breath Feline Friend

H2: What are cat dental treats and how do they work?

• Topics to cover: Cat dental treats
• Blog post to support section:
  Title: How Cat Dental Treats Work (& Why Your Kitty Needs Them)
  Keyword: how do cat dental treats work

H2: What are the benefits of cat dental treats?

• Topics to cover: Clean teeth, fresh breath
• Blog post to support section:
  Title: Do Cat Dental Treats Really Work? (Here’s What The Experts Say)
  Keyword: do cat dental treats work

H2: Are cat dental treats an acceptable alternative to brushing?

• Topics to cover: Cats dental health
• Blog post to support section:
  Title: Cat Dental Treats Vs Brushing: Everything You Need To Know
  Keyword: can cat dental treats replace brushing

H2: Do vets recommend using cat dental treats?

• Topics to cover: Veterinary oral health council
• Blog post to support section:
  Title: Vets Recommend Using Cat Dental Treats — Here’s Why
  Keyword: vet recommended cat dental treats

H2: The best cat dental treats to try

• Topics to cover: Purina dentalife, Feline greenies, natural ingredients, artificial flavors.
• Blog post to support section:
  Title: 5 Of The Best Cat Dental Treats & Why We Love Them
  Keyword: best cat dental treats
• Blog post #2 to support section:
  Title: What To Look For In Cat Dental Treats
  Keyword: what to look for in cat dental treats

Creating an outline for a pillar page isn’t easy, but once laid out, it helps us understand the content that needs to be produced to bring the whole thing to life.

Here is our list of content to create (based on our outline):

1. Pillar page: The Complete Guide to Cat Dental Treats: For a Fresh-Breath Feline Friend

2. Blog #1: How Cat Dental Treats Work (& Why Your Kitty Needs Them)

3. Blog #2: Do Cat Dental Treats Really Work? (Here’s What The Experts Say)

4. Blog #3: Cat Dental Treats Vs Brushing: Everything You Need To Know

5. Blog #4: Vets Recommend Using Cat Dental Treats — Here’s Why

6. Blog #5: 5 Of The Best Cat Dental Treats & Why We Love Them

7. Blog #6: What To Look For In Cat Dental Treats

The best way to tackle this list of content is to create and publish the six blog posts first, then once they are live, you can write the pillar page content, placing hyperlinks to the supporting blog posts directly in the copy.

2. Planning a pillar page from top performing content

For this next method, let’s say you already have a ton of published content about a particular topic, and you’d like to reuse and repromote that content within a pillar page dedicated to that topic.

All of the steps in the previous process apply, but for Step 2 (Select Related Keyword Ideas for Blog Content), do the following:

First, you’ll want to understand which of your existing pieces generates the most interest from your audience. Let’s use our web analytics data for this. In this example, we’ll look at Google Search Console data because it shows the actual search performance of our website content.

Let’s use the topic of “content creation” as our desired pillar page keyword. Search for the query in Google Search Console (choose the “Queries containing” option): 

Pull all of the pages currently generating impressions and clicks from terms containing your topic, placing those with the highest clicks and impressions at the top of your list. Here’s what this might look like: 

As you can see, most of the content we’ve created that also ranks for keywords containing “content creation” is blog content. These will be highly useful as related resources on our pillar page.

Now, go back to your TF-IDF tool and select the subtopics related to “content creation” that you want to cover in your pillar page. Example:

• Social media content

• Content creation tool

• Content creators

• Content strategy

• Content creation process

Finally, map your existing blog content to those “content creation” subtopics. The initial mapping may look something like this:

You may not be able to map each blog perfectly to the subtopic you’re covering in your pillar page, but that’s  OK. What’s important is that you’re providing readers with relevant content (where applicable) and that content, as you’ve seen in your Search Console data, is already proven to perform well with your organic search audience.

Pillar page planning templates and resources

Pillar pages take an incredible amount of time and planning to execute, but they are worth every penny.

Here’s an example of the success we saw after producing one of our more recent pillar pages, “How to Rank on Google:”

Growth of referring domains and links to the page since its launch in April 2022.

Here’s a template of the outline used to bring the page to life (and you can use it for your own pillar page). Just make a copy and off you go. Good luck!

Get Your Team Ready for a Productive Year — Next Level

Whether it’s a new year, new team or the same year, same team, it’s important to set yourself up for success. Every team has their own unique challenges when it comes to productivity and standardizing processes, but there are definitely a few steps you can take to mitigate them.

Before launching into a new project, new year, or new process, be sure everyone on your team has the tool access they need and is ready to tackle any task that comes their way. To that end, here are seven steps to get your team ready for a productive year using the Moz suite of tools!

1. Verify who manages your account (and subscription)

When it comes to ensuring things go smoothly, a critical step is knowing who manages, or owns, your Moz account. Account owners are able to manage subscriptions, add seated users, access invoices, update payment methods, and more.

So why is this step one on our list? When it comes to team success, it’s imperative to know who to reach out to when there’s an issue. For example, if you need to upgrade your subscription level or purchase add-ons, you will need to know who on your team is able to take care of those changes. Or, if you have a new team member who needs to be onboarded with the Moz tools, the account owner will need to add them as a seated user on your account.

Touch base with your team and verify who has owner access to your Moz subscription. If you’re not sure if you have owner access or not, log into your Moz account and head to Account and Billing. If you are the subscription owner, you’ll see your Moz Pro subscription, along with pricing and renewal date, listed under Moz Pro.

From the Account & Billing section of your account, if you do not see the price and renewal date for the subscription and you see Shared Subscriptions as a view option, this indicates you are a seated user on the account and do not have access to subscription management or seated user management.

2. Add seats to your account

Ensuring your team has access to the tools they need is imperative when it comes to setting them up for success. Adding seated users to your subscription allows them to customize the types of emails they receive, which Campaigns they follow, interact in the Q&A forum, and sign up for Moz Academy courses. All around, it’s a great idea for each person to have their own login and tool access.

Once you know who is managing your Moz Pro subscription, be sure to add your teammates as seated users. Only the owner of the account can add seated users, so if you’re not in charge of your subscription, be sure to reach out to the owner to get those teammates added. Additionally, if you don’t already have one in place, this would be a great time to define a process for requesting the addition and removal of seated users from your account.

You can add seated users to your subscription at any time via the Manage Seats section of Account & Billing.

3. Check your subscription limits

It’s a good idea to get in the habit of regularly checking your subscription limits. Are you close to maxing out your tracked keywords limit? Are you making more Link Explorer queries? Or maybe you’re nearing the top end of your Campaign limit? By keeping an eye on your subscription limits and how you’re using them, you can stay on top of your team’s needs throughout the year. That way, when it’s time to onboard a new client or do a deep dive into competitive research, you’re not scrambling to make changes to your subscription.

A quick reminder here: only the owner of the account can upgrade and/or purchase add-ons for your subscription. Just like with adding seats, this would be the perfect time to outline a procedure for requesting and implementing subscription changes that accounts for necessary budget approval timelines.

To check your subscription limits for your Moz Pro Campaigns, head to the Manage Your Campaigns screen. Your limits (also known as allowances), and how much you’re using of each, will be noted at the top of the page.

4. Follow (or unfollow) campaigns

Sharing a subscription with multiple team members may mean having multiple Campaigns. And Campaigns may be set up for different clients, markets, or tasks based on your team’s responsibilities and projects. When it comes to staying productive and keeping on task, you may opt to adjust which Campaigns you get emails for each week. Your current project may not require you to stay up to speed with your colleague’s client rankings, or you may be jumping in to help out with site audits of a high-value client while a teammate is out of the office. Regardless of the situation, be sure you and your team are taking advantage of the ability to customize which Campaigns you follow and, as a result, receive emails for.

In Moz Pro, following a Campaign means you will receive insight and update emails from the tool on a regular basis. You can follow and unfollow Campaigns from either the Manage Your Campaigns screen or from your Campaign Settings. From the Manage Your Campaigns screen, use the checkbox in the last column titled Following to change your settings. Or from within Campaign Settings, use the checkbox under General > Site Basics.

You can update your follow status at any time, which can allow for flexibility around projects and clients. Additionally, follow status is login specific which means each seated user can pick and choose which Campaigns to follow based on their needs.

5. Automate reporting

Whether you regularly send updates to clients, need to keep key stakeholders informed, or you just want to stay on top of important initiatives, you likely send reports regularly. Rather than taking the time to manually generate a new report every week or month, why not automate the process? Using Moz Pro’s Custom Reports feature can help you to streamline your reporting and send updates to whoever you choose on the regular.

Depending on your team’s needs and the projects you’re working on, you may opt to set up team-specific or task-specific reports:

• Team-specific reports may include overviews of various aspects of a Campaign such as the Dashboard view, Site Crawl Overview, and Rankings Overview to give a birds-eye view of the overall health of a client’s site. You can then set this up to send directly to your client, other members of your team, or your boss so they can stay up to speed.

• Task-specific reports take a deeper dive into a particular area of your Campaign. For example, you may be focused on improving a client’s crawlability or improving their rankings for a subset of keywords and decide to set up reports specific to those areas.

Regardless of the type of report you need to send, the Custom Report builder in Moz Pro will tell you how to get it set up and scheduled for regular delivery, right to the inboxes of the interested parties. You can choose a report template or build a report from scratch to make sure your report includes everything you need. You can even check out our Daily SEO Fix series for additional ideas, just in case you’re looking for a little extra guidance.

6. Enroll team members in free Moz Academy courses

Have new team members who aren’t familiar with the Moz tools? Or do you need a reminder about the metrics and functionalities of the tools? We’ve got you covered. Moz Academy offers two free tool-specific courses to help you get off on the right foot (or regain your footing if you just need a quick refresh).

The first is How to Use Moz Pro which is an in-depth overview of all the primary tools included in your Moz Pro subscription. Learn all about how to use Moz tools so you can hit the ground running. It includes detailed information about each aspect of the tools along with the metrics included and lessons to practice what you’ve learned.

The second is The Insider's Guide to Moz Pro: Your 4-Week SEO Game Plan which combines videos, tasks, and additional resources to help you implement an SEO strategy with the Moz Pro tools.

Both of these courses are fully on-demand, instructor-led, and self-paced. You can refer back to these lessons over and over in case you have a “how do I do that again?” moment, and they both offer additional learning resources throughout.

7. Get Certified!

Nothing can help a team be more productive and successful quite like being on the same page regarding processes and task management. And being up to speed on best practices, tips and tricks, and practical application is a critical component of that. It’s almost like the table of contents to the book of strategy — it gets you all to the right place where you can get down to business!

Moz Academy offers five different certifications, which can help get your team acquainted with various aspects of SEO strategy and implementation. We offer certifications in SEO Essentials, Technical SEO, Keyword Research, Competitive Analysis, and Local SEO. If you have the budget for team development, these courses can help make sure everyone on your team is ready to tackle any task. Once a certification is completed, you also receive a downloadable certificate and the opportunity to add a badge to your LinkedIn profile to show off your newly acquired skills.

Conclusion

Ensuring you and your team have the access and knowledge they need to be productive will help minimize hiccups throughout the year. By performing these steps up front, you’ll be able to onboard clients, perform research, and accomplish more in less time. After all, success is when preparation meets opportunity.

And with that, you’re ready to hit the ground running with your Moz account for any and all SEO projects you have coming up. If you’re looking to learn even more, don’t forget to keep an eye on the Moz Tools category of the Moz Blog for future Next Level posts as well as the Daily SEO Fix series.

An Apple Search Engine? – Whiteboard Friday

Happy Friday, Moz fans! In today's Whiteboard Friday episode, Tom digs into his research on Apple’s moves in search, specifically their recent launch of what he believes is a search engine, how it works, and how they could possibly hope to compete with Google in the future.

Click on the whiteboard image above to open a high resolution version in a new tab!

Video Transcription

Howdy, Moz fans. We're here today to talk about an Apple search engine. There have been rumors circulating for a couple of years now that Apple are building a search engine. I'm here to convince you I think they are building a search engine and I think they've already launched it.

"Apple won't be building a search engine"

But before we get into what does that look like, let's start off by talking about the common reasons people say, "Apple won't be building a search engine." The first is that we know that Google pay Apple something in the order of $18 billion to $20 billion dollars a year to be the default search engine on Apple devices. That's a lot of cash.

But if you consider Apple makes more than a billion dollars a day, probably not such a big idea as we think it is. But more importantly, in 2020, the Department of Justice in the U.S. said that they were going to be suing Google for monopoly practices. One of the four bullet points they listed as their reasons was that they don't want Apple being paid by Google to be the default search engine. They believe that's a monopoly practice.

They want it to stop. So even if Apple do care about the cash, it might be going away anyway. So then it was not necessarily a surprise, in 2018, we saw the head of search at Google leave and go to Apple. Apple hired the head of search. That's a very suspicious thing to do if you're not building a search engine. We also saw at the same time they started listing job listings for hundreds and hundreds of search engineers, which all adds up to building something search related.

Apple has launched a search engine

So rumors circulated, oh, Apple are going to build a search engine. It flew under the radar a little bit, but Apple already launched a web search engine. In iOS 14, we're on iOS 16 now, iOS 14 launched September 2020, Apple made a change where if you do a search in the iOS default search screen, the Siri suggested websites used to be powered by Google's web index, iOS 14 changed it to Apple's own web index.

They've already got a web index, and they've got a page on their website where they tell us about that web index. On that page, they describe how their Applebot works. They've got a web crawler that for the last three years or so can already render JavaScript, something that took Google 20 years or so before they had that. So they've got a mature crawler. On that page, they also outline their search ranking factors, their top five search ranking factors they have.

It's things like links, web page design characteristics, which sounds like Core Web Vitals and PageRank. So the search ranking factors look very similar to Google. They've got a crawler very similar to Google. On their page, they talk about how if you've got no Applebot specific rules in your robots.txt file, they'll follow Googlebot rules. So you can see the direction of travel.

They're trying to crawl the web in a similar shape to Google. But I think that's a distraction. I think there are several things that they could do differently if they wanted to build a bigger search engine, and we're going to talk about the three differences I think they could have that would allow them to build a search engine in a very novel way that would compete with Google in a way that we haven't necessarily fully understood.

Federated search

So let's talk about that. So the first thing is federated search. Consider how you do a search on Google. You type in "Madrid," and it goes and it looks in Google's one giant database. That database has a web index and a knowledge index and all of that stuff. But it's essentially looking in Google's own singular database. With Apple, it's tempting to think, okay, well, they've got a much smaller web index than Google.

They can just go and look in that. But what I actually think is they'll use a federated search approach. Federated search is when you delegate a search to multiple different providers and then aggregate the results. In Apple's case, I think they can delegate the search to all the apps on your device. Basically, you do a search for "Madrid," and rather than just looking in the web index, it might say, well, this Madrid search, the intent might be to book a hotel, so I'm going to look in the Hotels.com app.

The intent might be to book a flight, so I'm going to look in the Skyscanner or the Lufthansa app. It might be learn a language, Duolingo. It might get a travel guide, so you look at the Lonely Planet app. The point being that they would ask all of these devices and then blend the results from multiple different sources together. But how would they know what apps are on your device and cater to what intents?

Mobile native

In 2020, they rolled out a change to the operating system that allowed apps being installed on your device to register a list of intents that they can cater to, which is very interesting. It seems like 2020 is the year where they started launching a lot of these things and setting up for this potential search engine. So you would get a search that went to their web index, but also searched through the apps on your device and blended those results together.

As further evidence that they will blend these results, Apple managed to reverse engineer the API they use for their web index, and when you do searches, you get one list of results. You don't get web results and knowledge results. You get one big list of results, sorted by relevancy, and it might be news, web, web, maps, whatever .

The point being it shows Apple's thinking. They're concerned more with relevancy than where the results came from, and they're happy to blend them together. Okay, so they've got this federated search approach. So let's talk about how these searches can also have custom UIs. So when they rolled out the change to allow an app to cater to specific intents, that app can also tell the phone, oh, when you're catering to this specific intent, here's a snippet of user interface you can use outside of the app to cater to that in the best possible way.

As an example, if you ask Siri to split a check, it understands that the calculator app on your phone can cater to that intent. But it doesn't send you to the calculator app. Instead it shows a little custom UI snippet right there, in the search results, where it shows you how to split that check. So apps that have been installed on your phone can say, "I can deal with this sort of intent, and this is the best way to present that result to users."

It goes one step further. At the same time, they also launched App Clips. App Clips are what Apple describe as small parts of an app. What's important about App Clips is that they get streamed to your device. So you can scan a QR code or click a link and it will go straight into the App Clip. There's no need to install a full application on your device.

App Clips are designed to do one small part of what a full app would do, but basically frictionless in loading them up. So an example might be imagine you arrive in a city and you've not been there before. You're running late. So you do a search for "scooter," and rather than just searching the apps on your device, because Apple have got this database of App Clips and they've got almost 2.5 million apps in their App Store, they could also serve that intent.

So you search for "scooter," Apple say, "Yes, here's an App Clip that can help you with that." You press the button and you go straight into the app. It directs you to a nearby scooter. You pay for it with Apple Pay. You get on the scooter and off you go. This is a mobile native experience. You didn't go to any website. You didn't install an app. Everything happened right inside the search results. So Google have been moving to this mobile first paradigm, but it's still web first. With Apple, there's a potential for a mobile native experience. This is something that Google could only dream of. What is also true is that this federated search approach would allow Apple to completely bypass Google's strengths.

Google's strengths are the fact that they've got this huge web index and they've been building that for 25 years or whatever. With a federated search approach, Apple can cater to many of the same intents without needing to replicate Google's web index and their rankings and all of that magic. So if you're going to build a search engine, you probably also want to be able to personalize results.

Private personalization

How are Apple going to do that especially considering that they position themselves as the sort of privacy-centric tech company? So first thing, quickly consider the difference between Google Photos and Apple Photos. On Google Photos, they will do machine learning of all of your photos on their servers in the cloud, allowing you to say, "Oh, show me my photos of animals," for example.

You can also do "show me my photos of animals" with Apple Photos, but all of the machine learning happens on your device. It shows the two different paradigms. So when you do a search, Google will serve you some personalized search results based on your history or whatever it might be, but it's all happening in the cloud. What I think Apple will do is serve you a list of potential results from their web index, and then User A and User B would see a different subset of those chosen by their phone using the machine learning on the device, which understands your preferences, your history, what apps you've got installed, etc.

The final thing is that, in terms of personalization, Apple have a potential advantage here too because with the federated search approach, Apple can do what I call fully authenticated personalization. If you do a recipe search for a schnitzel recipe on Google, you'll get some personalized results, but it will be from the web index. If you do a schnitzel recipe search on your device, this federated search approach will allow Apple to look into your "private" databases.

If you've got the Recipe Keeper app, it will see, oh, yes, you've got a schnitzel recipe in the app. I'm going to pull that out. It might see that your mom sent you a message on Facebook about the best way to make schnitzel, so it will pull that out. This is stuff that Google can't do. Google can't look behind the curtain into your "private" databases. Over the last few years, I think Apple have been playing a slow game, laying the pieces to move towards this mobile native sort of experience.

So when I first started talking about this research in mid-2022, at the SearchLove Philadelphia conference, I predicted that Apple would move the search field onto the iOS home screen in order to try to change user behavior and push them towards doing this mobile native sort of search rather than having users go into a web browser to do a search.

Then a couple of weeks later, Apple announced they were doing exactly that, and that rolled out in iOS 16. September 2022 Apple made it so that the search field is right there on your home screen now, trying to push people towards doing this sort of search. What that means for us as SEOs is yet to be seen, whether they move in this sort of direction, but all the pieces seem to line up.

If you've got an app, this is definitely something that you should be thinking about. Otherwise, we should all be thinking about what this means for us over the next couple of years as Apple try to shift the user behavior. What that means is still to be seen. Thank you so much.

Video transcription by Speechpad.com

Renting vs. Owning the Post-Review Local Consumer Journey

Technology can be a conductor or a barrier. Everything we do to market local businesses is meant to culminate in a human encounter. When we get our part right (and external forces smile upon us), technology connects us. When we get our part wrong (or external forces impede us), technology can have the frustrating effect of sundering local brands from their customers, with everybody losing out on the deal.

The modern phenomenon of local search exemplifies the concept of a “mixed blessing”. Loss of control over significant parts of the customer journey can be a source of legitimate stress for owners and marketers. Stress isn’t good for us, of course, and that’s why I’m hoping this message brings some welcome relief: control of the most important aspects of the consumer journeys remains strongly on your side, and you can thrive without the parts you have to give up. We’ve got data to back this up, thanks to Moz’s recent report, The Impact of Local Business Reviews on Consumer Behavior, and I’m hoping today’s column will lift some burdens that may have been weighing you down.

The data

Let’s start out by taking a moment to really reflect on what it means that 96% of adults read local business reviews. Basically almost everyone in your community is perusing this content, making it the widest possible road to your front door, but the truth is that it exists in a space you only partially control. Given that only 11% of review-readers trust brand messaging over public opinion, reviews matter greatly, and it’s a tough reality that they mainly happen in digital spaces you rent rather than own.

If something goes wrong with your reviews on third party platforms like Google, Nextdoor, or Yelp, such as a spam attack, or the random disappearance of your reviews due to a bug or update, or a single irate customer shouting half-truths or downright falsehoods through a megaphone amid a small number of reviews, you have limited direct recourse for resolution. Platforms may or may not respond to your pleas for help, and some customers may ignore even your best offers to resolve their complaints – the sense of lost control is not imaginary.

Here is the good news: for 91% of your potential customers, the very next step they take after reading reviews will land them in spaces you own. 51% will head to your website, which you fully control, 27% will visit your place of business, which you also fully control, and 13% will contact you, and it's you who control your phone and text lines, your email, forms, and live chat. Apart from the 8% that will move from reviews to the profiles you rent on social media platforms, management of customer experiences is almost all on your side and in your house.

Barring mishaps like your website being infected with malware, a temporary closure of your premises due to illness, or a power outage bringing down your phone lines, it turns out that you remain in charge of key customer/brand experiences during nearly all of the post-review consumer journey. Great news, indeed! But it carries some big responsibilities with it.

Converting on the next step after reviews

The wide funnel begins to narrow as consumers transition from reading reviews to their next steps. Winning maximum conversions from their next actions depends on having the right welcome in place in all three of these spaces:

The local business website

Whether customers click from the review profile to your website homepage, or to a landing page your listing is linked to, prepare this welcome for them:

• An accessible, secure, technically-clean, optimized website housing the multi-media content and features the customer needs to take their next steps towards a transaction.

• Highly visible information on every way in which the customer can contact and visit you, including phone, text, chat, messaging, email, forms, hours of operation, maps, and written directions.

• Additional first-party reviews to provide further proofs of your good reputation and tide you over in times when bugs make your third-party reviews go missing.

• A unique selling proposition to seal the deal.

Your place of business

Whether your place of business is your physical premises, or your clients’ locations, you can shine on this main stage with the following:

• Exceptional customer service based on the training of your staff and good management of the entire customer service ecosystem. With 65% of review writers saying they’ve written negative reviews because of experiencing bad or rude customer service, building an employee-centric company that radiates both happiness and helpfulness is your best bet for building an excellent reputation.

• Careful guardianship of your supply chain. 63% of review writers say they’ve written negative reviews after purchasing bad products. The quality of your inventory supports both repeat purchases and high ratings.

• Accurate online local business listings. 52% of survey respondents have written negative reviews after encountering incorrect business information on the Internet. Use of listings management software like Moz Local can ensure that what’s published about your business online (like hours of operation, addresses, and key services) matches what the customer will experience in the real world, preventing inconvenience and disappointment.

Your contact options

Whether a review reader turns next to your phone line, text line, live chat, website form, or email, assist them towards a next conversion by:

• Reducing on-hold times on your phone line to the bare minimum

• Ensuring all public-facing representatives of the business are well-trained in your products, services and policies

• Providing realistic estimates of when a customer will hear back if they are required to leave an email address on chat instead of speaking immediately to a live person

• Reducing the number of form fields the customer is required to fill out before reaching you

• Offering an after-hours support option

• And, of course, for the 8% who will visit your rented spaces on social media platforms as their next step after reading reviews, be sure your full contact information is included on your profiles.

Despite the market disruption of the Internet, so much about local businesses remains the same

While technological innovations are ongoing, it’s apparent that deeply-rooted consumer behaviors continue to follow a traditional pattern that’s existed for hundreds of years. In summary, people in your town want to know what others say about your business >>> people want to connect with your business for a possible transaction >>> people then tell others about what they experienced with your business. All of this cycle has always happened offline, and the only real change is that the means for some of this communication has partly transitioned online.

Just as business owners always had to do without the ability of controlling the word-of-mouth reputation their community was creating for them on front porches and over fences, modern business owners can live without directly controlling the online brand sentiment that exists in spaces they have to rent rather than owning. While it’s true that traditional PR may have had more power to shape public perception before online local business reviews made individual consumer voices so loud, the not-so-secret ingredient to brand longevity and loyalty remains unaltered: great customer experiences at and around the time of service are the foundation of success.

What every local business needs today is a thoughtful plan for managing the digital assets that now contribute to these positive consumer experiences. The winning recipe, then, is developing high standards for the spaces you own (your website, place of business, and most contact methodologies) and being as hands-on as possible in the spaces you rent (the online profiles containing your local business information, reviews, and social content). With a workable strategy and good quality tools for managing this ecosystem, the development of your good name in the community you serve will follow.

Knowledge is power; read Moz’s full survey report: The Impact of Local Business Reviews on Consumer Behavior

ChatGPT Won’t Replace Google Search (Yet)

Even in the relentless news and noise of early 2023, you’ve probably heard about ChatGPT, the GPT-3-powered (technically, 3.5) chatbot that’s eerily able to simulate human-like responses. Consider, for example, this question and answer (created by GPT-3):

Is ChatGPT a search engine?

No, ChatGPT is not a search engine. It is an artificial intelligence chatbot that uses natural language processing to understand and respond to user input.

That’s not bad, and it sounds like something an actual human would write. 

GPT (Generative Pre-training Transformer) is a deep learning system that generates text based on predicting language patterns after being pre-trained with a large set of documents. For this post, I’ll be using OpenAI’s Playground with the “text-davinci-003” GPT-3 model, which can be programmed to produce shorter answers and is more reliable than the ChatGPT Beta.

The current models are genuinely impressive, including parsing complex questions:

How would you explain ChatGPT to a 5 year old?

ChatGPT is like a robot friend who can talk to you and answer your questions. It's like having a friend who knows a lot about different things and can help you learn new things.

GPT can even mimic human creativity, and make us start questioning our own talents:

Write a slogan for a Mars-themed restaurant run by lizard people, in the style of Edgar Allen Poe.

"Lizards of Mars, Dine Here In Splendor, Where Dreams Unfurl And Palates Render!”

By now, you’ve probably seen dozens of examples, so what does all of this have to do with Google Search and our jobs as search marketers?

Google and the era of natural language

In the early days of search, search engines were built to index words and short phrases and had no ability to process natural language. If you were looking for a new laptop, you might search for something like “laptop” or “buy laptop.” I sometimes joke that, if you walked into Best Buy and just started shouting “laptop!”, you’d probably be escorted out by security. We humans adapted to early search, though, and we dumbed down our language.

As search became more sophisticated, we learned that we could use more complex queries, and, especially with the advent of voice search, we experimented with something closer to natural language. As Google adapted, something interesting happened: our queries became questions, prompting Google to realize that sometimes we don’t want a link to a resource — we want an answer.

Google has evolved a great deal as an “answer engine,” including building out the Knowledge Graph and surfacing web results as direct answers known as Featured Snippets. If, for example, you search for “How does Google search work?”, you might get back a Featured Snippet (essentially, an attributed answer) like this:

This particular example is a little clunky, but it illustrates how the algorithm works. Google is looking for bits and pieces of documents that might answer the question. In this case, it’s obvious that the extracted passage isn’t really a complete answer.

Now, consider the same question posed to GPT-3:

How does Google search work?

Google Search works by crawling the web and indexing websites. When a user searches for something, Google looks through its index and returns the most relevant results. It uses a combination of algorithms and other techniques to determine the relevance of the results. These algorithms take into account factors such as the words used in the query, the freshness of the content, the popularity of the website, and the location of the user.

I can nitpick this answer, but all in all, it’s pretty good, and it’s a much more complete answer than an excerpt from a website. The GPT-3 engine has essentially summarized multiple sources.

It’s easy to see how this could start to make Google nervous.

Trust and the attribution problem

On the surface, GPT-3 (and especially ChatGPT) can return some pretty human-looking responses. Putting aside ethical questions (including plagiarism and bias, which I’ll cover briefly later), there are some serious practical problems.

The Google “answer” has one major advantage: attribution. We can easily go to the source page. This not only provides us more information, but it provides more context, including details about the source itself. Those details can help us trust (or, in some cases, distrust) the answer.

Consider, for example, another answer GPT-3 returned for the question above:

How does Google search work?

Google Search works by using a combination of algorithms and programs to analyze the content of web pages and other online content to determine its relevance to a user's search query. Google Search algorithms look for a variety of factors, including keyword density, freshness, and the number of other sites that link to the page. Google also uses artificial intelligence and machine learning to improve its search results.

This answer also sounds plausible, except that most SEOs would cringe at the mention of keyword density (underlining added by me), widely considered a myth. It’s entirely possible that this piece of information came from an entirely different source, but without attribution, we can’t validate it.

While this is a complex problem (machine-generated text doesn’t use sources in quite the same way a human dozen, or might use dozens or hundreds of sources), hybrid approaches that reduce the number of sources and provide attribution are possible.

Consider this answer from Neeva — an alternative search engine focused on privacy (hat tip to Greg Sterling) — for “Should I get a tall latte or a grande?”:

While this functionality is in beta and is obviously not operating at Google scale, Neeva attempts to provide primary sources. I’ve purposely chosen a ridiculous example because the stakes are low. Imagine a question squarely in what Google’s calls the YMYL (Your Money, Your Life) realm, such as “Is Bitcoin or Dogecoin better?”:

This is a question that could seriously impact my financial future, and knowing where the answer is coming from makes a big difference and allows me to dig deeper and either establish trust or reject those sources.

Related to trust is a deeper, ethical issue of whether machine-generated text is a form of plagiarism. While traditional plagiarism generally requires intent and copying sizable chunks of text, machine-generated text is still being built off of the backs of writers and content creators, without — at least in the case of ChatGPT — any clear attribution. In Google’s case, overuse of machine-generated text could discourage content creators and cause us to question whether we want to contribute our efforts to someone else’s machine.

Hallucinations and machine dreams

Without careful constraints, machine learning systems are prone to hallucination. In the case of ChatGPT, that essentially means that the system can generate answers that are not rooted in reality. Simply put, ChatGPT doesn’t understand anything it’s saying — it’s creating new patterns based on human language. Consider this nonsense question I posed to GPT-3:

What is Mozart's 1976 hit "The Fast and the Furious: Tokyo Drift" about?

Mozart's 1976 hit "The Fast and the Furious: Tokyo Drift" is not related to the 2006 film of the same name. It is an instrumental piece that captures the frenetic energy of Tokyo’s streets at night. The song is built around a catchy, syncopated piano line and a driving, upbeat rhythm.

While intriguing, there is no such instrumental piece. I’ve asked a nonsensical question and GPT-3 has obliged me with a nonsensical answer (Nonsense In, Nonsense Out).

I should point out that ChatGPT already has some constraints built in that address problems like this, and complex models (including OpenAI’s GPT-3 interface) allow you to control “randomness” (high randomness = less constraints), but the core problem is challenging.

Again, consider a higher-risk financial question:

What's more popular: Dogecoin, Bassetcoin, or Norwegianlundehundcoin?

Dogecoin is by far the most popular of the three coins, with a current market capitalization of over $9 billion. Bassetcoin and Norwegianlundehundcoin are much smaller coins with market caps of only a few hundred thousand dollars each.

A market cap of a few hundred thousand dollars each is pretty impressive for two cryptocurrencies that (as of this writing) don’t exist. I’m sorry to say that I started this example with Labradoodlecoin, only to discover that Labradoodlecoin actually exists.

I’m pushing the engine pretty hard to prove a point here, and modern machine-generated text is much less prone to hallucination than previous iterations. That said, any time you combine multiple sources without regard to their veracity or completeness, there’s a real risk that the end result will be plausible-sounding nonsense.

Scale and the real-time internet

This one’s pretty straightforward: What works at beta scale may not work at Google scale. As the late Bill Slawski would point out, just because Google has an idea — or even patents an idea — doesn’t mean that they implement that idea in search (for many reasons).

Another issue is the sheer speed of the internet. ChatGPT is trained on a static corpus — a moment in time. Google crawls and indexes the internet very quickly and can return information that is recent, localized, and even personalized.

It’s worth noting that Google has invested massive amounts of money into machine learning. Google’s LaMDA (Language Model for Dialogue Applications) is capable of generating complex, human-like text. Google is well aware of the limitations and costs of these models. If they’ve moved slowly in deploying them across search, there are probably good reasons.

While the topic of bias is far beyond the scope of this article, scale also contributes to bias issues. Once you move on from a static, controlled corpus and open up machine learning models to the entire world of real-time content, human bias creeps in quickly (including racism, sexism, homophobia, and other destructive biases). At Google scale, reducing bias is a problem that requires a lot of human intervention and resources.

Code red and future threats

None of this is to suggest that Google doesn’t take GPT (including ChatGPT) seriously. Google reportedly issued a “code red” after ChatGPT went viral. While Google is understandably quiet about their internal reactions, it is almost certain that recent developments are accelerating discussions and developments in Mountain View.

Another clear threat is that Microsoft is an investor (to the tune of $1 billion) in OpenAI (and, with it, ChatGPT), and rumors are circulating that they may invest billions more. Microsoft has also announced that they will start integrating ChatGPT into Bing search before the end of March, although it’s unclear what from that initial rollout will take.

One of the biggest long-term impacts of models like ChatGPT and LaMDA will be in conversational search (including, but not limited to, voice search). Consider the following “conversation” I had with ChatGPT (edited for length):

What are the top five three-row SUVs?

It's difficult to say which are the top five three-row SUVs as it can be subjective and depend on factors such as personal preference, budget, and location. However, some three-row SUVs that are often considered to be among the best in their class include:

• Honda Pilot

• Toyota Highlander

• Kia Telluride

• Hyundai Palisade

• Subaru Ascent

Which of them is the least expensive?

Out of the five SUVs that I mentioned, the Subaru Ascent tends to be the least expensive with a starting price around $32,295. The other SUVs that I mentioned have a starting price around $32,000 - $38,000. However, it's important to note that the final price can vary depending on the specific trim level and options that are selected.

Is the Subaru generally considered reliable?

Subaru is generally considered to be a reliable automaker, with many of their vehicles receiving high marks for dependability. The Subaru Ascent, in particular, has a reputation for being a reliable vehicle with a comfortable interior and good fuel economy. According to Consumer Reports, the Ascent gets an above-average reliability score.

Sorry, ChatGPT can definitely get chatty (and this is the edited version). Note the follow-up questions and how I didn’t need to repeat information or provide context. ChatGPT understood that I wanted to build on previous answers.

While this model won’t serve all of the use cases of search, there are definitely situations where the ability to easily and conversationally refine a query could be revolutionary, especially for complex questions, and, yes, complex purchases. Imagine Google being able to serve different ads at each step on this journey toward a purchase.

Unfortunately, the biggest short-term threat to Google is that people and companies will likely use ChatGPT to churn out mountains of low-quality content, costing Google time and money and likely resulting in major, reactive algorithm updates. This will also be a serious headache for search marketers, who will have to react to those updates.

What’s certain for 2023 is that the popularity of ChatGPT and its accessibility to the general public is going to cause an explosion of investment (for better or worse) and accelerate development. While Google isn’t going anywhere, we can expect the landscape of search to change in unexpected (and occasionally unwanted) ways in the next year.

Daily SEO Fix: Investigating Keyword Cannibalization

Keyword cannibalization occurs when a website has too many similar keywords spread throughout the various pages on that site. This can harm the SEO potential of the pages involved, and can quite often go unnoticed for some time. When more than one page has the same, or a similar keyword target, those pages will then start to compete with each other, also creating confusion in the eyes of the search engine, resulting in a struggle to decide which page to rank for what term.

Remember: a single URL can rank for multiple keywords, which is 100% fine. The problem of keyword cannibalization occurs when two or more separateURLs are all competing for the same keyword.

To ensure that a website’s best content is ranking well, you should identify which of your pages are targeting the same keywords. You can then put together a strategy for monitoring and fixing these issues on a regular basis.

In this Daily SEO Fix edition, we take you through what keyword cannibalization is, how to investigate it on your own website, and how to solve any potential issues your site may have. 

Buckle up!

Learn More in Moz Academy’s Keyword Research Certification

What is Keyword Cannibalization?

First, Samantha will define keyword cannibalization, and explain why it should ultimately be avoided.

Use Moz Tools to Investigate Keyword Cannibalization

In this video, Emilie will talk through how to investigate potential keyword cannibalization issues with Moz Pro’s Keyword Explorer tool.

Solutions for Cannibalization

In this video, Emilie will discuss potential solutions to tackle cannibalization issues.

---

Learn more about keyword cannibalization:

• Whiteboard Friday: Keyword Cannibalization
• How to Identify and Tackle Keyword Cannibalization

What Is a Core Update? – Whiteboard Friday

Recorded at SearchLove London in October — in the wake of three Google updates — Tom presents a different take on core updates in this Whiteboard Friday.

Click on the whiteboard image above to open a high resolution version in a new tab!

Video Transcription

Happy Friday, Moz fans. So I'm here at SearchLove London recording this Whiteboard Friday. I don't know when it will reach you, but this is a bit of a different take on how to think about core updates. So obviously, I'm filming this in October. We've just had three updates back-to-back in quick succession.

I think it's quite interesting that we had three updates and they were described in very different ways. So we had a helpful content update, a core update, and a product update or a product review update. It's interesting that sometimes Google talks about updates very specifically. So I think the best examples are things like HTTPS, or Core Web Vitals, page experience update, where they're very concrete about what they're going to do, how they're going to do it, how they're going to measure it, and how it's going to impact the algorithm.

Then you have core updates, where they do say things, but they tend to be kind of saying the same thing every time. So every single core update, they've said make good content, work on your expertise, authoritativeness, trust. This isn't very concrete. It's not very specific about what they've changed this particular time.

Indeed, if you're a site that's affected by these updates, it can feel quite random. It can feel like you're just going upwards or downwards. There's no particular rhyme or reason. So how can that be? So I want to give you some different ways to think about that.

A refresh

So the two different ways that I'd like to focus on, one of them is this concept of a refresh. So Google used to talk a lot about algorithm refreshers. This is up till about 2012. What they meant was this is something that was different to an algorithm update. So it wasn't called an update. It was called a refresh, as distinct. They were trying to say that this would kind of be like a mini reset of how the algorithm was thinking about certain things.

If you look at how they talk about core updates in their documentation, they say things like this, "So your site might not recover until the next core update." So you'd have situations where this is your rankings in blue. This is your competitor's rankings in red. You get to a point where they've improved their site over time gradually. They've not been recognized for it, and then a core update comes along and suddenly they go up. So your position, you go down, and you're left thinking, "Oh, that was a little bit random." But, of course, it wasn't random. It was just that they were gradually being recognized for things they've worked on or suddenly being recognized for things they've worked on gradually over time.

Testing

The other concept I'd like to talk about is the extent to which Google is testing. They're iteratively testing over time. Again, they talk about this in their own documentation. There's an article that I've come back to quite a few times, back in 2018, it'll probably be linked beneath, where they invited some journalists to a meeting of their search engineering team. In that meeting, they were talking about how they were thinking about some changes they were making to the SERPs, and they talked a lot about how they were going to run some things as a test and look at certain metrics, see how they were improved. So it's important to think that Google has their own metrics that they're iterating towards, and they're not necessarily saying, "Oh, your site is bad," or, "There's something wrong with your site." They might be saying, "Oh, well, what we're aiming for at this point could be more beneficially affecting some sites than others. Ultimately, if someone comes up, someone else has to go down."

Indeed, in MozCast data, if we look at sites that were affected by at least four updates, so this is looking since Medic, technically there were some core updates before Medic, but I think the industry has been very focused on this since Medic, if we look at the core updates, of which there have been 12 now, and the sites that were affected by at least 4 of them, the vast majority in MozCast data had both some major positive movements and some major negative movements. So this tiny green slice represents the sites that only saw positive movements, and this red slice, the sites that only saw negative movements. So it's incredibly unusual to have mono-directional movement, which just shows that people are winning and losing as Google tests different things. It's not necessarily that some sites are just better suited to core updates and win every time. That's very, very rare.

Longer term

I also want to talk a little bit about the longer term. I think it's important, when we think about these updates, to zoom out of it because these short-term effects can seem more random, harder to explain, harder to predict. So I've looked at a lot of sites again in the MozCast data over time and how they've been impacted by each update.

So this is an example, and obviously, it's drawn on a whiteboard, so it's not super precise. But this example I've attempted to illustrate here is actually Reuters, the news organization. I've chosen them because this is a site that obviously produces a lot of original content. It's very authoritative. It's hard to criticize it from the regards that Google likes to talk about in its core updates discussions and announcement. These bars represent how it was affected by each core update over a period of time. So it had some big negative hits, not many serious gains from these updates. So this doesn't look very good. But if you track how their traffic grew or their visibility grew within MozCast over time, it looks a little bit different. So it sort of gradually grows over time. So what this means is even though on the days of the specific updates they were taking sometimes negative hits, like if we look at the week before and the week afterwards, sometimes they took big hits. Obviously, there's long periods of time between these updates, so they might still be able to grow.

So say there might be three months between these bars, and even though they took a big hit here, they're growing over the next three months. Maybe over here, they take this big hit, but they've more than recovered it by the time they get to the next update, take this hit, more than recovered it by the time they get to the next one. That could be that their SEO team is working some magic behind the scenes, but this is quite a consistent trend. This happens to a lot of sites. What I would suspect is actually happening is Google, when they launched the core update, they're, to some degree, resetting certain things, looking at things afresh, valuing different metrics. Then over time, whatever historically was making that site perform will creep back in and start to be considered again.

So I hope that was interesting. That's just a few different ways to think about core updates besides the usual messaging that we get, which is very consistently just E-A-T, good content. I'm not saying you shouldn't do those things. Those are important. This longer-term trend that you get with a lot of sites that do do those things shows how important it is. But I think when you look at individual updates, you have to keep in mind that it's not necessarily that Google is suddenly optimizing for these things more. They're just iterating over time. That's all from me. Thanks.

Video transcription by Speechpad.com