SEO
Trending Content Output Compared in ChatGPT, Gemini & Claude
“Should we use ChatGPT, Gemini, or Claude to create trending content?”
That’s a good question – and one that I’m frequently asked when teaching a live class about engaging audiences through content.
You might mistakenly assume that instructors are supposed to answer questions like that. But my colleagues and I do something different.
We give our students relevant assignments that provide them with the opportunity to discover the answers to good questions for themselves.
This test-and-learn approach is something that you can also apply within your own company, agency, or team. Want to know which generative AI model to use to create trending content?
Well, conduct a test and compare the output.
Write Concise Descriptions Of The Most Emotionally Engaging Video Ads Of Euros 2024
You already know how to use Google Trends to identify search terms or topics that are trending now. In fact, many journalists use this free tool to get story ideas.
Over the long Fourth of July weekend, I used Google Trends and saw that the topic “Euros 2024” ranked No. 1 in Trending Searches with more than 1 million queries.
Next, I decided to avoid using OpenAI’s ChatGPT 3.5 for my tests. Why? Because it’s the most popular generative AI model, which means that your competitors are probably using it, too.
That means the content that this tool creates is less likely “to provide substantial value when compared to other pages in search results,” as Google’s long-standing advice recommends.
ChatGPT Output
So, I explored the custom versions of ChatGPT and selected Write For Me by puzzle.today.
Why? Because it ranked No. 1 in the Writing category. The tool also claimed it would help me “write tailored, engaging content with a focus on quality, relevance and precise word count.”
I want to create better content, not just content that is different from what everyone else is creating. So, I asked Write For Me to “write concise descriptions of the most emotionally engaging video ads of Euros 2024.”
Here’s what this generative AI tool produced:
1. Unity Through Football
“A diverse group of children from different European countries come together on a pristine football pitch. As they play, the camera captures their joy and camaraderie, transcending language and cultural barriers. The ad concludes with a montage of professional players joining the children, emphasizing football's power to unite nations and foster friendship.”
2. Legacy of Legends
“The ad begins with black-and-white footage of iconic moments from past Euros, highlighting legendary players. It transitions to vibrant, modern clips of current stars recreating these moments, symbolizing the passing of the torch. A heartfelt narration speaks to the continuity of dreams and the legacy carried by each generation.”
3. Homecoming
“A montage of fans traveling from various parts of Europe to the host country, capturing their excitement and anticipation. Emotional reunions with fellow fans, old friends, and family members create a sense of belonging and community. The ad closes with a panoramic shot of a stadium filled with cheering supporters, underscoring the tournament's role in bringing people together.”
4. The Dream Begins
“The ad follows a young aspiring footballer practicing tirelessly, inspired by their favorite Euros moments. Interspersed with clips of professional matches, it shows the child's journey from local games to a stadium filled with fans. The message is clear: dreams start small but can lead to greatness, encouraging viewers to pursue their passions.”
5. Heartbeat of the Game
“This ad features a rhythmic sequence of football-related sounds: the thud of a ball, cheers from the crowd, and the whistle of the referee. These sounds build into a symphony, interspersed with clips of players’ intense focus and emotional celebrations. The heartbeat sound underscores the passion and excitement of the Euros, resonating with fans’ own emotions.”
6. From Streets to Stadiums
“Children playing football in urban alleys, rural fields, and makeshift pitches across Europe are showcased. Their raw passion and joy are mirrored by professional players in grand stadiums, blurring the lines between dreams and reality. The ad concludes with a powerful message: football belongs to everyone, from the streets to the grandest arenas.
Now, it’s perfectly clear why video ads with these descriptions would be emotionally engaging, but it is frustratingly unclear which brands are running these ads during Euros 2024.
So, I’d have to do some double-checking to make sure that ChatGPT isn’t hallucinating.
Gemini Output
Next, I gave Google’s Gemini (formerly Bard) the same prompt. Here’s what this generative AI model produced:
1. Adidas: "Hey Jude" (Most Engaging)
“This ad features rising England star Jude Bellingham alongside football legends like David Beckham and Frank Lampard. It taps into positive emotions by showcasing the passing of the torch and the enduring spirit of the game.”
2. Irn-Bru: "Get to Germany"
“This ad, likely using humor, aims to create positive feelings and excitement around the Euros being held in Germany.”
3. Budweiser: "Bring it Home"
“This ad uses a patriotic theme, likely aiming to inspire viewers and evoke a sense of national pride for their team's chance to win the Euros.”
It’s perfectly clear which brands are running the most emotionally engaging video ads of Euros 2024, but it’s still unclear which methodology Gemini is using to make this selection.
So, I’d still have to do more due diligence to discover that it’s probably recent articles and posts about new research from DAIVID.
Claude Output
I asked Anthropic’s Claude 3.5 Sonnet to “write concise descriptions of the most emotionally engaging video ads of Euros 2024.” Here’s what this generative AI tool replied:
“I apologize, but I don't have access to specific information about video ads from Euro 2024, as my knowledge cutoff is in April 2024, and I can't browse the internet for current information.”
“I can, however, offer some general thoughts on what makes emotionally engaging soccer/football ads:”
“Underdog stories of players or teams overcoming adversity.”
“Nostalgic montages showcasing historic Euro moments.”
“Depictions of passionate fans and their connection to the sport.”
“Inspirational messages about unity and international cooperation.”
“Cinematic recreations of iconic goals or plays.”
“If you'd like me to expand on any of these concepts or discuss emotionally engaging sports ads in general, I'd be happy to do so. For accurate information about Euro 2024 ads, I'd recommend checking official UEFA sources or recent sports media coverage.”
Well, Claude’s honesty is admirable. But its knowledge cutoff means that I shouldn’t use this generative AI model for content about fairly recent trends.
Write Short Captions For The Funniest Photos From The 2024 Nathan’s Hot Dog Eating Contest
For my second test, I used the Google autocomplete feature to confirm that the phrase, [Nathan’s hot dog eating contest], was a trending search term.
Then, I asked each of the three generative AI tools to “write short captions for the funniest photos from the 2024 Nathan’s Hot Dog Eating Contest.”
ChatGPT Output
Here’s what Write For Me generated:
“Captions for Funniest Photos from the 2024 Nathan’s Hot Dog Eating Contest:”
"When you realize you're only halfway through your 50 hot dogs."
"Eyes on the prize: the ketchup bottle!"
"Training for this by swallowing my pride daily."
"When the bun hits you harder than the hot dog."
"Mustard not? I mustered up the courage!"
"New strategy: inhale, don’t chew."
"Hot dogs: 10, Dignity: 0."
"When you think it’s the last dog but it’s not."
"The face you make when you beat your personal best... by 1 dog."
"Calories don’t count if you don’t chew, right?"
Okay, I admit that many of these captions are funny. But it’s difficult to tell if they belong to actual photos or if this custom version of ChatGPT hallucinated the entire list.
And don’t get me started on getting permission to use any photos that exist. Of course, I could always use DALL-E 3 to turn the text above into images.
Gemini Output
Next, I gave Gemini the same assignment. Here’s what it generated:
1. Mustard Mishap: "Someone's about to be redecorated in yellow!" (Photo of a competitor with mustard splattered all over their face).
2. Relish the Moment: "This is what pure competitive joy looks like." (Photo of a competitor mid-devour with a look of intense concentration and relish dripping down their chin).
3. Bun Bungee: "Is that a hot dog or a bungee jumper? Defying the laws of physics, one frankfurter at a time." (Photo of a competitor with a hot dog halfway down their esophagus).
4. Fountain of Fury: "Looks like someone forgot their manners! (But they're probably winning.)" (Photo of a competitor with a spray of water and ketchup erupting from their mouth).
5. Doggy Downtime: "Even champions gotta rest sometimes. (Just don't let Joey Chestnut see this.)" (Photo of a competitor slumped back in their chair with a belly full of hot dogs).”
Um, okay. These are also funny captions.
But it’s hard to know if they go with actual photos that were posted on July 4, 2024, without using Google Images to conduct a series of relevant searches. And that still doesn’t give me permission to use them even if they do exist.
[Note, these responses were generated a few days before Google announced their support for labelling AI-generated images.]Claude Output
Then, I asked Claude 3.5 Sonnet to “write short captions for the funniest photos from the 2024 Nathan’s Hot Dog Eating Contest.” Here’s what it replied:
“I apologize, but I don't have access to specific photos from the 2024 Nathan's Hot Dog Eating Contest, as my knowledge cutoff is in April 2024. Additionally, I can't generate, produce, edit, manipulate or create images.”
“However, I can suggest some hypothetical humorous captions that might be appropriate for funny moments at a hot dog eating contest:”
"When the hot dogs fight back"
"Regretting that 50th hot dog"
"Mid-contest nap: Expert level achieved"
"Ketchup everywhere... except on the hot dogs"
"When you realize it's only been 2 minutes"
"The face of a champion... or indigestion"
"Spectators' faces: Equal parts horror and awe"
"When the bun-to-dog ratio is all wrong"
"Competitive eating: Where table manners go to die"
"That moment you question all your life choices"
“Remember, these are fictional captions for imaginary photos. For accurate information about the 2024 contest, you'd need to check official sources or news reports from after the event.”
Once again, Claude gets high marks for being honest about its limitations.
But unless I want to select some of these hypothetical humorous captions and use them as prompts in Adobe Firefly, then I need to use one of the other options.
Write A 400-Word Blog Post About The Top Omni Channel Retailing Trends Of 2024
For my third test, I used SparkToro to research the audience of 5,000 to 6,000 people who search for the keyword [customer retention] each month.
I used SparkToro’s trending keywords feature to analyze the search terms that have risen in popularity among searchers for “customer retention” over the last quarter.
Then, I selected the trending keyword, “omni channel retailing trends,” for this test.
ChatGPT Output
When I asked Write For Me to “write a 400-word blog post about the top omni channel retailing trends of 2024,” here’s what this generative AI tool produced:
Top Omnichannel Retailing Trends of 2024
“As we move into 2024, the landscape of retail continues to evolve rapidly, driven by technological advancements and changing consumer expectations. Omnichannel retailing, which integrates various shopping channels into a seamless customer experience, remains at the forefront of this evolution. Here are the top omnichannel retailing trends to watch out for in 2024.”
1. Enhanced Personalization Through AI and Data Analytics
“In 2024, personalization goes beyond just using the customer’s name in emails. Retailers are leveraging advanced AI and data analytics to offer hyper-personalized shopping experiences. By analyzing consumer behavior, preferences, and purchase history, retailers can tailor recommendations, promotions, and content to individual customers. This level of personalization enhances customer satisfaction and increases conversion rates.”
2. Seamless Integration of Physical and Digital Channels
“The line between online and offline shopping continues to blur. In 2024, more retailers are perfecting the integration of physical and digital channels. Innovations like in-store augmented reality (AR) mirrors, smart fitting rooms, and mobile app functionalities that enhance in-store experiences are becoming standard. Additionally, services like click-and-collect and in-store returns for online purchases are expected to become more streamlined and widespread.”
3. Expansion of Mobile Commerce (M-Commerce)
“Mobile commerce continues to grow as consumers increasingly use their smartphones for shopping. Retailers are optimizing their mobile websites and apps to provide faster, more intuitive, and secure shopping experiences. Features like one-click purchasing, mobile wallets, and personalized push notifications are becoming essential components of mobile strategies.”
4. Social Commerce Revolution
“Social media platforms are transforming into powerful retail channels. In 2024, social commerce, where shopping experiences are embedded within social media, is set to explode. Platforms like Instagram, Facebook, and TikTok are enhancing their shopping functionalities, allowing users to discover, browse, and purchase products without leaving the app. Influencer marketing and user-generated content continue to drive this trend, making social media a critical part of omnichannel strategies.”
5. Sustainable and Ethical Retailing
“Consumers are increasingly demanding sustainability and transparency from the brands they support. In response, retailers are incorporating sustainable practices and ethical sourcing into their omnichannel strategies. This includes offering eco-friendly products, reducing packaging waste, and providing transparency about product origins and manufacturing processes. Brands that can effectively communicate their sustainability efforts through all channels will gain a competitive edge.”
6. Voice Commerce and Conversational AI
“Voice-activated shopping and conversational AI are becoming more prevalent. With the rise of smart speakers and virtual assistants, consumers are using voice commands to search for products, place orders, and track deliveries. Retailers are integrating voice commerce capabilities into their omnichannel strategies to enhance convenience and improve customer engagement.”
Conclusion
“In 2024, the retail industry is embracing these omnichannel trends to create more cohesive and engaging shopping experiences. By focusing on personalization, integrating physical and digital channels, leveraging mobile and social commerce, prioritizing sustainability, and adopting voice commerce, retailers can stay ahead in a competitive market. These trends highlight the importance of flexibility and innovation in meeting the evolving needs of modern consumers.”
Um, okay. This is 498 words long. This content seems designed for publication at the beginning of the year.
The blog post is missing citations from reliable sources, credible quotes, and relevant statistics, as Roger Montti’s article, “Researchers Discover How To SEO For AI Search,” noted back on Dec. 18, 2023.
So, it’s not as bad as a first draft. But I would hope that writers would learn by using this custom version of ChatGPT that they need to craft something a little bit better.
Gemini Output
Next, I asked Gemini to tackle the same assignment. Here’s what this generative AI tool produced:
The Future of Shopping: Top Omnichannel Retail Trends in 2024
“The retail landscape is ever-evolving, and 2024 is no exception. Consumers today expect a seamless shopping experience, regardless of whether they're browsing online, visiting a physical store, or interacting with a brand on social media. This is where omnichannel retail thrives. By creating a unified experience across all touchpoints, retailers can build stronger customer loyalty and drive sales.”
“Let's delve into the top omnichannel retail trends shaping the industry in 2024:”
1. The Rise of the Data-Driven Experience:
“With the demise of third-party cookies, retailers are focusing on collecting and utilizing first-party customer data. This data allows for real-time personalization across all channels. Imagine receiving targeted email promotions based on your recent in-store purchases, or seeing personalized product recommendations on a brand's app. Advanced analytics will not only personalize marketing efforts but also optimize search functionalities and product merchandising on e-commerce platforms.”
2. AI Takes Center Stage:
“Artificial intelligence (AI) is rapidly transforming the retail experience. AI-powered chatbots can answer customer queries 24/7, recommend products based on browsing history, and even assist with in-store tasks. Generative AI can create personalized marketing content at scale, while AI-driven sales automation streamlines processes for both retailers and customers.”
3. The Blur Between Physical and Digital:
“The lines between online and offline shopping are continuing to blur. We're seeing a rise in ‘phygital’ experiences, such as augmented reality (AR) apps that allow customers to virtually try on clothes or visualize furniture in their homes. In-store kiosks can facilitate online purchases and allow for easy returns or exchanges. Additionally, ‘showrooming,’ where customers browse in-store and then purchase online, necessitates seamless product availability and pricing across channels.”
4. Social Commerce Takes Off:
“Social media platforms are no longer just for browsing; they're becoming powerful shopping destinations. ‘Live shopping’ experiences with influencers showcasing products are gaining traction, while social media platforms are integrating smoother buying functionalities within their apps. User-generated content and social proof will continue to influence purchasing decisions, making social media a crucial touchpoint in the omnichannel journey.”
5. Personalization Beyond Products:
“The future of omnichannel retail goes beyond just product recommendations. Retailers are focusing on creating personalized experiences that cater to individual customer preferences. This could involve offering flexible delivery options, loyalty programs with tiered benefits, or the ability to curate in-store shopping experiences through appointments or personalized product selections.”
Conclusion:
“In today's competitive retail environment, omnichannel isn't just a trend; it's a necessity. By embracing these trends and prioritizing a data-driven, personalized approach, retailers can not only survive but thrive in the ever-evolving landscape of commerce.”
Well, the headline is better and it’s 433 words long, which is closer to what I’d asked for. But this blog post is also missing citations from reliable sources, credible quotes, and relevant statistics.
So, I hope writers would learn the same lesson by using Gemini that they learned using a custom version of ChatGPT: It’s not bad, but a human with experience and expertise can do better.
Claude Output
Finally, I asked Claude 3.5 Sonnet to “write a 400-word blog post about the top omni channel retailing trends of 2024.” Here’s what this generative AI tool produced:
Top Omnichannel Retailing Trends Shaping 2024
“As we navigate through 2024, the retail landscape continues to evolve rapidly. Omnichannel strategies have become more crucial than ever, with consumers expecting seamless experiences across all touchpoints. Let's explore the key trends defining omnichannel retailing this year.”
1. AI-Powered Personalization: “Artificial intelligence is revolutionizing how retailers understand and cater to individual customer preferences. In 2024, we're seeing more sophisticated AI algorithms that analyze customer data across channels to deliver hyper-personalized recommendations, offers, and experiences.”
2. Augmented Reality Integration: “AR is bridging the gap between online and offline shopping. Retailers are leveraging AR technology to allow customers to virtually try on clothes, visualize furniture in their homes, or explore products in detail before making a purchase decision.”
3. Social Commerce Acceleration: “Social media platforms are increasingly becoming direct sales channels. Retailers are optimizing their presence on platforms like Instagram, TikTok, and Pinterest, enabling in-app purchases and creating shoppable content that seamlessly integrates with users' social experiences.”
4. Sustainable and Ethical Omnichannel Practices: “Consumers are more environmentally conscious than ever. Retailers are responding by implementing sustainable practices across their omnichannel operations, from eco-friendly packaging to transparent supply chains and ethical sourcing information available across all channels.”
5. Voice Commerce Integration: “With the growing adoption of smart speakers and voice assistants, retailers are optimizing their digital presence for voice search and enabling voice-activated purchases, adding another dimension to the omnichannel experience.”
6. Phygital Experiences: “The blend of physical and digital experiences, or ‘phygital,’ is gaining traction. Retailers are creating innovative in-store digital touchpoints and bringing elements of the physical store experience to online platforms.”
7. Unified Customer Data Platforms: “Retailers are investing in advanced customer data platforms that consolidate information from all channels, providing a single view of the customer and enabling more cohesive marketing and service strategies.”
8. Flexible Fulfillment Options: “The line between online and offline continues to blur with the expansion of services like buy online, pick up in-store (BOPIS), curbside pickup, and same-day delivery. Retailers are optimizing their logistics to offer customers maximum flexibility.”
9. Subscription-Based Models: “More retailers are incorporating subscription services into their omnichannel strategies, providing regular product deliveries or exclusive access to content and experiences across multiple platforms.”
10. Advanced Analytics for Real-Time Insights: “Retailers are leveraging advanced analytics tools to gain real-time insights into customer behavior across channels, allowing for quick adjustments to inventory, pricing, and marketing strategies.”
“As these trends show, the future of retail lies in creating cohesive, customer-centric experiences that seamlessly blend online and offline touchpoints. Retailers who successfully adapt to these omnichannel trends will be well-positioned to thrive in the dynamic retail environment of 2024 and beyond.”
Claude’s content is 443 words long, which is longer than Gemini’s, but shorter than the custom version of ChatGPT. And Claude generated 10 trends, while ChatGPT generated six, and Gemini generated five.
But just like the other generative AI tools, Claude’s blog post is missing citations from reliable sources, credible quotes, and relevant statistics.
So, Claude is also good at creating a rough draft. But I’d hope that writers would learn by using ChatGPT, Gemini, and Claude that they shouldn’t become a tool of their tools.
AI Is Not Going To Take Your Job
A year ago, Jensen Huang, the founder, president, and CEO of Nvidia, said,
“AI is not going to take your job. The person who uses AI is going to take your job.”
Well, a year later, we’ve learned by comparing the content output generated by ChatGPT, Gemini, and Claude that it’s still smarter to use generative AI tools to brainstorm or create a good first draft.
Then, use your experience, expertise, authoritativeness, and trustworthiness (E-E-A-T) to add emotionally engaging videos, eye-catching photos, citations from reliable sources, credible quotes, and relevant statistics to your content.
Why? Because this is the best way to provide substantial value when compared to other pages in search results.
More resources:
Featured Image: jomel alos/Shutterstock
SEO
How to Revive an Old Blog Article for SEO
Quick question: What do you typically do with your old blog posts? Most likely, the answer is: Not much.
If that’s the case, you’re not alone. Many of us in SEO and content marketing tend to focus on continuously creating new content, rather than leveraging our existing blog posts.
However, here’s the reality—Google is becoming increasingly sophisticated in evaluating content quality, and we need to adapt accordingly. Just as it’s easier to encourage existing customers to make repeat purchases, updating old content on your website is a more efficient and sustainable strategy in the long run.
Ways to Optimize Older Content
Some of your old content might not be optimized for SEO very well, rank for irrelevant keywords, or drive no traffic at all. If the quality is still decent, however, you should be able to optimize it properly with little effort.
Refresh Content
If your blog post contains a specific year or mentions current events, it may become outdated over time. If the rest of the content is still relevant (like if it’s targeting an evergreen topic), simply updating the date might be all you need to do.
Rewrite Old Blog Posts
When the content quality is low (you might have greatly improved your writing skills since you’ve written the post) but the potential is still there, there’s not much you can do apart from rewriting an old blog post completely.
This is not a waste—you’re saving time on brainstorming since the basic structure is already in place. Now, focus on improving the quality.
Delete Old Blog Posts
You might find a blog post that just seems unusable. Should you delete your old content? It depends. If it’s completely outdated, of low quality, and irrelevant to any valuable keywords for your website, it’s better to remove it.
Once you decide to delete the post, don’t forget to set up a 301 redirect to a related post or page, or to your homepage.
Promote Old Blog Posts
Sometimes all your content needs is a bit of promotion to start ranking and getting traffic again. Share it on your social media, link to it from a new post – do something to get it discoverable again to your audience. This can give it the boost it needs to attract organic links too.
Which Blog Posts Should You Update?
Deciding when to update or rewrite blog posts is a decision that relies on one important thing: a content audit.
Use your Google Analytics to find out which blog posts used to drive tons of traffic, but no longer have the same reach. You can also use Google Search Console to find out which of your blog posts have lost visibility in comparison to previous months. I have a guide on website analysis using Google Analytics and Google Search Console you can follow.
If you use keyword tracking tools like SE Ranking, you can also use the data it provides to come up with a list of blog posts that have dropped in the rankings.
Make data-driven decisions to identify which blog posts would benefit from these updates – i.e., which ones still have the chance to recover their keyword rankings and organic traffic.
With Google’s helpful content update, which emphasizes better user experiences, it’s crucial to ensure your content remains relevant, valuable, and up-to-date.
How To Update Old Blog Posts for SEO
Updating articles can be an involved process. Here are some tips and tactics to help you get it right.
Author’s Note: I have a Comprehensive On-Page SEO Checklist you might also be interested in following while you’re doing your content audit.
Conduct New Keyword Research
Updating your post without any guide won’t get you far. Always do your keyword research to understand how users are searching for your given topic.
Proper research can also show you relevant questions and sections that can be added to the blog post you’re updating or rewriting. Make sure to take a look at the People Also Ask (PAA) section that shows up when you search for your target keyword. Check out other websites like Answer The Public, Reddit, and Quora to see what users are looking for too.
Look for New Ranking Opportunities
When trying to revive an old blog post for SEO, keep an eye out for new SEO opportunities (e.g., AI Overview, featured snippets, and related search terms) that didn’t exist when you first wrote your blog post. Some of these features can be targeted by the new content you will add to your post, if you write with the aim to be eligible for it.
Rewrite Headlines and Meta Tags
If you want to attract new readers, consider updating your headlines and meta tags.
Your headlines and meta tags should fulfill these three things:
- Reflect the rewritten and new content you’ve added to the blog post.
- Be optimized for the new keywords it’s targeting (if any).
- Appeal to your target audience – who may have changed tastes from when the blog post was originally made.
Remember that your meta tags in particular act like a brief advertisement for your blog post, since this is what the user first sees when your blog post is shown in the search results page.
Take a look at your blog post’s click-through rate on Google Search Console – if it falls below 2%, it’s definitely time for new meta tags.
Replace Outdated Information and Statistics
Updating blog content with current studies and statistics enhances the relevance and credibility of your post. By providing up-to-date information, you help your audience make better, well-informed decisions, while also showing that your content is trustworthy.
Tighten or Expand Ideas
Your old content might be too short to provide real value to users – or you might have rambled on and on in your post. It’s important to evaluate whether you need to make your content more concise, or if you need to elaborate more.
Keep the following tips in mind as you refine your blog post’s ideas:
- Evaluate Helpfulness: Measure how well your content addresses your readers’ pain points. Aim to follow the E-E-A-T model (Experience, Expertise, Authoritativeness, Trustworthiness).
- Identify Missing Context: Consider whether your content needs more detail or clarification. View it from your audience’s perspective and ask if the information is complete, or if more information is needed.
- Interview Experts: Speak with industry experts or thought leaders to get fresh insights. This will help support your writing, and provide unique points that enhance the value of your content.
- Use Better Examples: Examples help simplify complex concepts. Add new examples or improve existing ones to strengthen your points.
- Add New Sections if Needed: If your content lacks depth or misses a key point, add new sections to cover these areas more thoroughly.
- Remove Fluff: Every sentence should contribute to the overall narrative. Eliminate unnecessary content to make your post more concise.
- Revise Listicles: Update listicle items based on SEO recommendations and content quality. Add or remove headings to stay competitive with higher-ranking posts.
Improve Visuals and Other Media
No doubt that there are tons of old graphics and photos in your blog posts that can be improved with the tools we have today. Make sure all of the visuals used in your content are appealing and high quality.
Update Internal and External Links
Are your internal and external links up to date? They need to be for your SEO and user experience. Outdated links can lead to broken pages or irrelevant content, frustrating readers and hurting your site’s performance.
You need to check for any broken links on your old blog posts, and update them ASAP. Updating your old blog posts can also lead to new opportunities to link internally to other blog posts and pages, which may not have been available when the post was originally published.
Optimize for Conversions
When updating content, the ultimate goal is often to increase conversions. However, your conversion goals may have changed over the years.
So here’s what you need to check in your updated blog post. First, does the call-to-action (CTA) still link to the products or services you want to promote? If not, update it to direct readers to the current solution or offer.
Second, consider where you can use different conversion strategies. Don’t just add a CTA at the end of the post.
Last, make sure that the blog post leverages product-led content. It’s going to help you mention your products and services in a way that feels natural, without being too pushy. Being subtle can be a high ROI tactic for updated posts.
Key Takeaway
Reviving old blog articles for SEO is a powerful strategy that can breathe new life into your content and boost your website’s visibility. Instead of solely focusing on creating new posts, taking the time to refresh existing content can yield impressive results, both in terms of traffic and conversions.
By implementing these strategies, you can transform old blog posts into valuable resources that attract new readers and retain existing ones. So, roll up your sleeves, dive into your archives, and start updating your content today—your audience and search rankings will thank you!
SEO
How Compression Can Be Used To Detect Low Quality Pages
The concept of Compressibility as a quality signal is not widely known, but SEOs should be aware of it. Search engines can use web page compressibility to identify duplicate pages, doorway pages with similar content, and pages with repetitive keywords, making it useful knowledge for SEO.
Although the following research paper demonstrates a successful use of on-page features for detecting spam, the deliberate lack of transparency by search engines makes it difficult to say with certainty if search engines are applying this or similar techniques.
What Is Compressibility?
In computing, compressibility refers to how much a file (data) can be reduced in size while retaining essential information, typically to maximize storage space or to allow more data to be transmitted over the Internet.
TL/DR Of Compression
Compression replaces repeated words and phrases with shorter references, reducing the file size by significant margins. Search engines typically compress indexed web pages to maximize storage space, reduce bandwidth, and improve retrieval speed, among other reasons.
This is a simplified explanation of how compression works:
- Identify Patterns:
A compression algorithm scans the text to find repeated words, patterns and phrases - Shorter Codes Take Up Less Space:
The codes and symbols use less storage space then the original words and phrases, which results in a smaller file size. - Shorter References Use Less Bits:
The “code” that essentially symbolizes the replaced words and phrases uses less data than the originals.
A bonus effect of using compression is that it can also be used to identify duplicate pages, doorway pages with similar content, and pages with repetitive keywords.
Research Paper About Detecting Spam
This research paper is significant because it was authored by distinguished computer scientists known for breakthroughs in AI, distributed computing, information retrieval, and other fields.
Marc Najork
One of the co-authors of the research paper is Marc Najork, a prominent research scientist who currently holds the title of Distinguished Research Scientist at Google DeepMind. He’s a co-author of the papers for TW-BERT, has contributed research for increasing the accuracy of using implicit user feedback like clicks, and worked on creating improved AI-based information retrieval (DSI++: Updating Transformer Memory with New Documents), among many other major breakthroughs in information retrieval.
Dennis Fetterly
Another of the co-authors is Dennis Fetterly, currently a software engineer at Google. He is listed as a co-inventor in a patent for a ranking algorithm that uses links, and is known for his research in distributed computing and information retrieval.
Those are just two of the distinguished researchers listed as co-authors of the 2006 Microsoft research paper about identifying spam through on-page content features. Among the several on-page content features the research paper analyzes is compressibility, which they discovered can be used as a classifier for indicating that a web page is spammy.
Detecting Spam Web Pages Through Content Analysis
Although the research paper was authored in 2006, its findings remain relevant to today.
Then, as now, people attempted to rank hundreds or thousands of location-based web pages that were essentially duplicate content aside from city, region, or state names. Then, as now, SEOs often created web pages for search engines by excessively repeating keywords within titles, meta descriptions, headings, internal anchor text, and within the content to improve rankings.
Section 4.6 of the research paper explains:
“Some search engines give higher weight to pages containing the query keywords several times. For example, for a given query term, a page that contains it ten times may be higher ranked than a page that contains it only once. To take advantage of such engines, some spam pages replicate their content several times in an attempt to rank higher.”
The research paper explains that search engines compress web pages and use the compressed version to reference the original web page. They note that excessive amounts of redundant words results in a higher level of compressibility. So they set about testing if there’s a correlation between a high level of compressibility and spam.
They write:
“Our approach in this section to locating redundant content within a page is to compress the page; to save space and disk time, search engines often compress web pages after indexing them, but before adding them to a page cache.
…We measure the redundancy of web pages by the compression ratio, the size of the uncompressed page divided by the size of the compressed page. We used GZIP …to compress pages, a fast and effective compression algorithm.”
High Compressibility Correlates To Spam
The results of the research showed that web pages with at least a compression ratio of 4.0 tended to be low quality web pages, spam. However, the highest rates of compressibility became less consistent because there were fewer data points, making it harder to interpret.
Figure 9: Prevalence of spam relative to compressibility of page.
The researchers concluded:
“70% of all sampled pages with a compression ratio of at least 4.0 were judged to be spam.”
But they also discovered that using the compression ratio by itself still resulted in false positives, where non-spam pages were incorrectly identified as spam:
“The compression ratio heuristic described in Section 4.6 fared best, correctly identifying 660 (27.9%) of the spam pages in our collection, while misidentifying 2, 068 (12.0%) of all judged pages.
Using all of the aforementioned features, the classification accuracy after the ten-fold cross validation process is encouraging:
95.4% of our judged pages were classified correctly, while 4.6% were classified incorrectly.
More specifically, for the spam class 1, 940 out of the 2, 364 pages, were classified correctly. For the non-spam class, 14, 440 out of the 14,804 pages were classified correctly. Consequently, 788 pages were classified incorrectly.”
The next section describes an interesting discovery about how to increase the accuracy of using on-page signals for identifying spam.
Insight Into Quality Rankings
The research paper examined multiple on-page signals, including compressibility. They discovered that each individual signal (classifier) was able to find some spam but that relying on any one signal on its own resulted in flagging non-spam pages for spam, which are commonly referred to as false positive.
The researchers made an important discovery that everyone interested in SEO should know, which is that using multiple classifiers increased the accuracy of detecting spam and decreased the likelihood of false positives. Just as important, the compressibility signal only identifies one kind of spam but not the full range of spam.
The takeaway is that compressibility is a good way to identify one kind of spam but there are other kinds of spam that aren’t caught with this one signal. Other kinds of spam were not caught with the compressibility signal.
This is the part that every SEO and publisher should be aware of:
“In the previous section, we presented a number of heuristics for assaying spam web pages. That is, we measured several characteristics of web pages, and found ranges of those characteristics which correlated with a page being spam. Nevertheless, when used individually, no technique uncovers most of the spam in our data set without flagging many non-spam pages as spam.
For example, considering the compression ratio heuristic described in Section 4.6, one of our most promising methods, the average probability of spam for ratios of 4.2 and higher is 72%. But only about 1.5% of all pages fall in this range. This number is far below the 13.8% of spam pages that we identified in our data set.”
So, even though compressibility was one of the better signals for identifying spam, it still was unable to uncover the full range of spam within the dataset the researchers used to test the signals.
Combining Multiple Signals
The above results indicated that individual signals of low quality are less accurate. So they tested using multiple signals. What they discovered was that combining multiple on-page signals for detecting spam resulted in a better accuracy rate with less pages misclassified as spam.
The researchers explained that they tested the use of multiple signals:
“One way of combining our heuristic methods is to view the spam detection problem as a classification problem. In this case, we want to create a classification model (or classifier) which, given a web page, will use the page’s features jointly in order to (correctly, we hope) classify it in one of two classes: spam and non-spam.”
These are their conclusions about using multiple signals:
“We have studied various aspects of content-based spam on the web using a real-world data set from the MSNSearch crawler. We have presented a number of heuristic methods for detecting content based spam. Some of our spam detection methods are more effective than others, however when used in isolation our methods may not identify all of the spam pages. For this reason, we combined our spam-detection methods to create a highly accurate C4.5 classifier. Our classifier can correctly identify 86.2% of all spam pages, while flagging very few legitimate pages as spam.”
Key Insight:
Misidentifying “very few legitimate pages as spam” was a significant breakthrough. The important insight that everyone involved with SEO should take away from this is that one signal by itself can result in false positives. Using multiple signals increases the accuracy.
What this means is that SEO tests of isolated ranking or quality signals will not yield reliable results that can be trusted for making strategy or business decisions.
Takeaways
We don’t know for certain if compressibility is used at the search engines but it’s an easy to use signal that combined with others could be used to catch simple kinds of spam like thousands of city name doorway pages with similar content. Yet even if the search engines don’t use this signal, it does show how easy it is to catch that kind of search engine manipulation and that it’s something search engines are well able to handle today.
Here are the key points of this article to keep in mind:
- Doorway pages with duplicate content is easy to catch because they compress at a higher ratio than normal web pages.
- Groups of web pages with a compression ratio above 4.0 were predominantly spam.
- Negative quality signals used by themselves to catch spam can lead to false positives.
- In this particular test, they discovered that on-page negative quality signals only catch specific types of spam.
- When used alone, the compressibility signal only catches redundancy-type spam, fails to detect other forms of spam, and leads to false positives.
- Combing quality signals improves spam detection accuracy and reduces false positives.
- Search engines today have a higher accuracy of spam detection with the use of AI like Spam Brain.
Read the research paper, which is linked from the Google Scholar page of Marc Najork:
Detecting spam web pages through content analysis
Featured Image by Shutterstock/pathdoc
SEO
New Google Trends SEO Documentation
Google Search Central published new documentation on Google Trends, explaining how to use it for search marketing. This guide serves as an easy to understand introduction for newcomers and a helpful refresher for experienced search marketers and publishers.
The new guide has six sections:
- About Google Trends
- Tutorial on monitoring trends
- How to do keyword research with the tool
- How to prioritize content with Trends data
- How to use Google Trends for competitor research
- How to use Google Trends for analyzing brand awareness and sentiment
The section about monitoring trends advises there are two kinds of rising trends, general and specific trends, which can be useful for developing content to publish on a site.
Using the Explore tool, you can leave the search box empty and view the current rising trends worldwide or use a drop down menu to focus on trends in a specific country. Users can further filter rising trends by time periods, categories and the type of search. The results show rising trends by topic and by keywords.
To search for specific trends users just need to enter the specific queries and then filter them by country, time, categories and type of search.
The section called Content Calendar describes how to use Google Trends to understand which content topics to prioritize.
Google explains:
“Google Trends can be helpful not only to get ideas on what to write, but also to prioritize when to publish it. To help you better prioritize which topics to focus on, try to find seasonal trends in the data. With that information, you can plan ahead to have high quality content available on your site a little before people are searching for it, so that when they do, your content is ready for them.”
Read the new Google Trends documentation:
Get started with Google Trends
Featured Image by Shutterstock/Luis Molinero