SEO Is Not That Hard

Why using ChatGPT for Keyword Research is a bad idea

Edd Dawson Season 1 Episode 181

Send us a text

Ever wondered if ChatGPT is the magic bullet for your keyword research? The truth might surprise you. Join me, Ed Dawson, as I unravel why relying on artificial intelligence for SEO tasks could actually undermine your strategy. With over 20 years of experience in building and monetizing websites, I bring an insider's perspective on the pitfalls of using language models like ChatGPT. These models, while adept at mimicking human conversation, fall short in accessing the real-time, actionable data that is crucial for crafting successful SEO strategies.

In this eye-opening episode, I explain how ChatGPT’s lack of access to live search data and trends can lead you astray. We’ll explore the critical importance of understanding search intent and keyword difficulty—areas where traditional SEO tools far outshine language models. You'll learn why optimizing for keywords without accurate intent analysis could misalign your content with your audience's needs, thereby sabotaging your efforts. Tune in to discover valuable insights and avoid common pitfalls in your keyword research journey.

SEO Is Not That Hard is hosted by Edd Dawson and brought to you by KeywordsPeopleUse.com

You can get your free copy of my 101 Quick SEO Tips at: https://seotips.edddawson.com/101-quick-seo-tips

To get a personal no-obligation demo of how KeywordsPeopleUse could help you boost your SEO then book an appointment with me now

See Edd's personal site at edddawson.com

Ask me a question and get on the show Click here to record a question

Find Edd on Twitter @channel5

Find KeywordsPeopleUse on Twitter @kwds_ppl_use

"Werq" Kevin MacLeod (incompetech.com)
Licensed under Creative Commons: By Attribution 4.0 License
http://creativecommons.org/licenses/by/4.0/

Speaker 1:

Hello and welcome to. Seo is not that hard. I'm your host, ed Dawson, the founder of keywordspeopleusecom, the place to find and organise the questions people ask online. I'm an SEO developer, affiliate marketer and entrepreneur. I've been building and monetising websites for over 20 years and I've bought and sold a few along the way. I'm here to share with you the SEO knowledge, hints and tips I've built up over the years.

Speaker 2:

the SEO knowledge, hints and tips I've built up over the years. Hi, welcome back to. Seo is not that hard. It's me, ed Dawson, as usual, hosting, and today I'm going to be talking about why using ChatGPT for keyword research is a bad idea a very bad idea, if you ask me. So yeah, if you've been using ChatGPT for trying to find your next top ranking keywords, then you might want to listen, because I'll break down for you why it's not the best approach.

Speaker 2:

So first of all, let's talk about what ChatGPT and other large language models are actually built for. So these models are designed to understand and generate human-like text. They're fantastic at things like answering questions, summarizing information, writing emails and even marketing copy, and they're trained on these big, huge data sets that cover all kinds of information from around the web and other sources, and that's why they seem so knowledgeable on a variety of topics. But and here's the difference they're not trained specifically on the kind of real-time, constantly updating data that we use in search engine optimization. They're missing that fundamental part, which is that real search engine insights. So chat utility doesn't have access to the keywords people are searching for right now. They don't have access to trends that are gaining momentum or search volumes associated with those terms. You know that's the big problem. So let's look into each of these bits kind of in detail. So let's look Lack of real search data. So, yeah, llms, they're trained on these live data sets but they're not connected to live search data from Google or any other search engine. So this means they don't know current trends. They don't have insights into which keywords have high or low search volume. You know real, proper seo tools, such as keywords people use or other tools like hrs, no semrush. They use data pulled directly from search engines that give accurate search volumes, difficulty scores, all those things like the people use with. The people also ask data that's live pulls from Google. We know that's live data, we know those are live trends, whereas the LLMs they are based on data sets that go back much further and also those data sets don't have that information about what people are actually searching for. So they might have read the web pages, but they have no idea of how people are searching the web and how people are using those web pages, how popular web pages. They don't know these things. There's no search intent analysis.

Speaker 2:

So we all know that understanding search intent is really critical for really good, effective SEO. So search engines they categorize keywords into, you know, informational, navigational, commercial, transactional intent, so probably a lot of intents in between that, but you know those are the main ones. So when you're searching google, google's trying to figure out what you mean, what you're trying to achieve with that search query, and will serve you content that's based upon that intent. So you know, an llm might be like a guess based on the phrasing, but they can't reliably categorize keywords based by intent, on the actual search engine data, because google knows for each query what kind of content people interact with most, what the kind of content I should try to find based on those user behaviors, whereas the llms don't have that data. So you could end up optimizing for keywords that don't align with your target audience's intent from the content that you're providing them. Llms don't have any keyword difficulty or competition analysis. You know it's essential with SEO to understand, you know how difficult something is to do, what the competition are like. Google data can tell you that because google knows how people interact with sites. Again going back to what I said with us on the search intent, they know how people are interacting, they know how many um you know sites. People you know have got linked, the sites they've got, they've got this whole kind of map of the web and how people interact with it. The alms don't.

Speaker 2:

The fourth thing is there's a lack of regional language specificity. So this is because the LLMs, they don't really know how different people in different countries are using the search engines and the kind of content they're after. So, for example, keywords people use, you can set the language, you can set the country and we'll only get data for you based on that language and country from Google and from other sources, whereas ChatGPT doesn't have level of filtering to be able to get you exactly the terms people are using in different countries and different languages, like we can with real-time data, and get you exactly the terms people are using in different countries and different languages, like we can with real-time data. And the big fifth one yeah, no real-time updates. You know SEO changes all the time. Trends change all the time, search engine algorithms happen frequently. Chatgpt doesn't receive real-time update or have access to live search data, so it can't reflect these shifts. You're always going to be looking at a point in time, generally many months or even more than a year past the point where you are now. So that lack of real-time data update is a real big miss when it comes to using ChatGPT.

Speaker 2:

So let's now look at it from the other side. Look at it from the side of why an seo tool is superior to chat gpt for things like keyword research. So first, you know we've got comprehensive data access. You know seo tools pulling data directly from search engines. Many will use google's own apis or scrape google to get sort of accurate real-time data so they're able to see how trends are changing, how seasonal fluctuations occur and also things like the competitive landscape for keywords.

Speaker 2:

Secondly, keyword suggestions and related terms. So like yes, a huge advantage of a tool like Keywords People Use, for example, is that we don't just give you a keyword, we also suggest those related terms and those intent chains. If you look at the people also ask and you can see how you know from a seed um keyword, a seed question, we can then find all the questions around the subsequent intent chains of follow-up questions that follow each one whereas which comes from real data rather than from just an educated guess which an LLM will make. Then there's filtering. Third, one's filtering. You know, with a tool you can filter that data, you can query that data. You can sort of drill down into it and interrogate it to get the right things that you need to know to make the right decisions for the content that you need to be creating, and so you know.

Speaker 2:

Fourthly, historical data. You know within keywords people use, you can start collecting historical data across. You know see keywords, for people also ask terms of other things. With the Search Console integration, you know we now have the historical data of how your keywords are ranking against your content over time, and this kind of historical context and perspective is something you can't get with chat, gpt.

Speaker 2:

But then you know, and I've just dug, had a real dig at chat gpt through all this. But you know chat gpt can be useful. Okay, right, I've told you why it should be used for keyword research, but it doesn't mean to completely useless for seo, you know. So, so to be completely for keyword research, but it doesn't mean it's completely useless for SEO. So, to be completely fair to it, it is good for some things. So here are some things it's actually good at. So, for example, generating content ideas. So you know LLMs they're not great at finding keywords, but once you've found those keywords using the SEO tool, you give those keywords to the large language model. It can really help you brainstorm content topics. So if you've got that that target list of keywords, use it with chat gpt to generate article ideas to help you build out some topics around those keywords. Really useful for that.

Speaker 2:

Secondly, it's good for drafting. You know meta descriptions or summaries. So you know if you've built some content and you want to have a great meta description or you want a great summary for that post, then you know chat gpt can be really good at things like that. And thirdly, you know content optimization suggestions. So you know they can be really good at suggesting ways to improve readability, add context or or break down topics. So that's where ChatGPT can be a really good thing, but obviously always be careful about how you use it so that you don't get hit by Google or anyone else for just using pure AI content.

Speaker 2:

You should consider ChatGPT as an assistant, as something to do all the work for you.

Speaker 2:

There's got to be something human that everything's based on in the first instance.

Speaker 2:

So, to wrap up, I mean you know, while ChatGPT and you know they're really incredible tools, you know, compared to what we had just a few years ago and they're getting better all the time, they're still not built to handle data-intensive requirements of SEO keyword research.

Speaker 2:

If you're serious about ranking and driving traffic, you need to use tools that pull real-time data based on how people actually use the web, based on that content graph, on that link graph, on that usage graph that Google has, and use tools like it was people use that. Mine those data sources of how people are really using it to work out what content you should be creating in the first place, what keywords you should be going after. Use that data that you can mine out of your Google Search Console, and that's how you've heard me talking about in recent episodes, about how we can now integrate with your Google search console, pull out all the data of how you actually are ranking in Google, where you're getting impressions, frequency of impressions, where you're missing out, and how we can compare your site and compare that data about how google's seeing your site, how people are using your site, and then help you build better content around that to optimize for that. That's something that chat gpt can't do.

Speaker 2:

Okay, it can't do that you know you can ask it to do that and it might give you what sounds like a sounds like a reasonable answer, but it's it's guessing, it's not actually based on data, and that's the key thing that you need to take away from this is that you know seo tools are based around that data, that key data, and understanding your site and understanding your data okay, so that's it for today.

Speaker 2:

I hope you found it useful hope it's you know, made it clear what the difference are between the two approaches, and one is clearly better than the other. Um, you've got any questions or any comments on this. Do let me know. Love to hear from people and well, until next time I'll see you later.

Speaker 1:

Before I go, I just want to let you know that if you'd like a personal demo of our tools that keywords people use, that you can book a free, no obligation one-on-one video call with me where I show you how we can help you level up your content by finding and answering the questions your audience actually have. You can also ask me any SEO questions you have. You just need to go to keywordspeopleusecom slash demo where you can pick a time and date that suits you for us to catch up Once again. That's keywordspeopleusecom slash demo and you can also find that link in the show notes of today's episode. Hope to chat with you soon. Thanks for being a listener. I really appreciate it. Please subscribe and share. It really helps.

Speaker 1:

Seo is not that hard. It's brought to you by keywords people usecom, the place to find and organize the questions people ask online. See why thousands of people use us every day. Try it today for free at keywords people usecom to get an instant hit of more seo tips. Then find the link to download a free copy of my 101 quick seo tips in the show notes of today's episode. If you want to get in touch, have any questions, I'd love to hear from you. I'm at channel 5. On twitter, you can email me at podcast at keywordspeopleusecom. Bye for now and see you in the next episode of seo is not that hard?

People on this episode