chatgpt for seo best and worst use cases with timestamps YoutubeScribe.com

[0:00] I'm sure you've seen tons of ChatGPT use
cases because they're literally everywhere.
[0:07] ChatGPT is insanely cool but most of
the use cases you've seen in Twitter
[0:13] or LinkedIn Threads or YouTube videos
are mostly hype up for engagement bait.
[0:18] So in this video, I'm going to share some
of the best and worst ChatGPT use cases
[0:24] for SEO – prompts, responses, and all.
[0:28] Let's start with one of the "best" use cases
for ChatGPT and that's to construct regex.
[0:33] Regex, or regular expression is a sequence of
characters that's used to find patterns within text.
[0:39] And ChatGPT is great at it.
[0:42] For example, if we want to find keywords
phrased as a question in Search Console,
[0:47] I can ask my buddy Chat…
[0:48] "What is the regular expression to show matches
that contain any of the following words in it: how,
[0:53] what, who, when, where, why, do?
[0:56] By the way, these words should
be the first word in the match."
[1:01] Now, armed with this answer, I'll go to Search
Console, paste that custom regex into the query
[1:06] filter and set my Positions filter
to greater than 10.
[1:10] Sort the list in ascending order and now we
have a list of informational keywords we can
[1:14] work on bringing from page 2
to page 1 of Google.
[1:18] Now, beyond Regex, ChatGPT can actually 
write full out automations for you.
[1:23] And this is one of my favorite ChatGPT use
cases for SEOs because it's going to make
[1:28] your work more efficient.
[1:30] Here's an example:
[1:31] Let's say you're working on
a link building campaign.
[1:33] You've collected the first and last names of
authors you want to contact and of course
[1:38] you have the URL and domain.
[1:40] The inefficient way to find these emails
would be to go through them 1 by 1 in
[1:44] a web app or with a Chrome Extension.
[1:46] The efficient way would be to code something in
Appscripts to connect to an email finding API.
[1:52] The ChatGPT way would be to have
the program write the code for you.
[1:57] So I'll type in: "Using Hunter.io's "Email Finder"
API, write a function called findEmail in Google
[2:04] Appscripts to return a person's email address.
[2:07] If no email exists, then return
"They don't want to be contacted".
[2:12] I will provide the first name,
last name, and domain name.
[2:15] Btw, my API key is this. Go!"
[2:22] Now I'll take that code, and open
Appscripts from the extensions menu.
[2:26] Let's paste in the code from my
good pal Chat and save the file.
[2:30] Give permissions as needed and
we're now back to the sheet.
[2:33] In the email column, I'll type in "findEmail",
open parentheses, click the first name,
[2:38] last name, and the domain.
[2:42] Hit Enter and you're all set.
[2:44] As for the rest of your list, just drag the formula
down and you're now finding emails at a much
[2:50] faster pace.
[2:51] There are literally hundreds of throwaway or quick
hacky tools you can use ChatGPT for to make your
[2:57] SEO more efficient but the show must go on.
[3:00] Because the next use case is one of
the worst that I've seen from ChatGPT,
[3:04] yet tons of people are raving about it.
[3:07] And that's doing AI-driven keyword research.
[3:11] So a common prompt people use on Twitter
and LinkedIn is to ask ChatGPT for long-tail
[3:16] or "easy-to-rank-for" queries.
[3:19] And at first glance, this list in
the golf niche doesn't look so bad.
[3:23] But you throw them into a keyword research
tool and you realize that pretty much none of
[3:28] them have search demand.
[3:30] And Google Trends shows
the same trend - or lack thereof.
[3:34] As for the "easy-to-rank-for" part, this just literally
makes no sense because keyword difficulty will
[3:40] mostly come down to backlinks, SERP
competition, and the actual content itself.
[3:46] But ChatGPT isn't even able to browse the web.
[3:49] All this negativity has got me feeling down
so let's talk about a use case that I've been
[3:54] using quite a lot recently and that's
coming up with clickworthy titles.
[3:59] Just ask ChatGPT to write 10 click-worthy
titles for your blog post on a topic.
[4:04] For the best results, give it a working
title especially if you have a specific
[4:09] angle you're going for to match search intent.
[4:12] In fact, you can even ask it to frontload
keywords if something isn't compromisable
[4:16] for you.
[4:18] Want more personality?
[4:19] You can even ask ChatGPT to make
your titles sound like a Mr. Beast video.
[4:23] I like this one.
[4:25] So let's actually use this for our next use
case which is to create quick outlines.
[4:30] In my opinion, this is one of the best use cases
for ChatGPT simply for efficiency purposes.
[4:37] The point isn't to get a ready-to-go outline
because you're feeling lazy – it's to get
[4:42] your creative juices flowing.
[4:43] For example, if I were creating a blog
post on this topic, I'd talk about this
[4:48] part a lot sooner, probably cut this
part, and add in something like this.
[4:53] In fact, I don't even like the title anymore so
I'd run with the angle of "Best and Worst
[4:59] Chat GPT Use Cases for SEO" – which
is the video you're watching now.
[5:04] Now, I am curious to see what kind of use cases
ChatGPT would offer me so let's ask it to expand
[5:09] on use cases for point III.
[5:12] And uh-oh…
[5:12] It's actually offered two awful use cases
right here in the content generation section.
[5:18] Let's talk about this one on generating
so-called "high-quality content" – more
[5:23] specifically, long-form content creation.
[5:27] When you ask ChatGPT to write you a full
article, the content is almost always going
[5:32] to come out as boilerplate content.
[5:35] It'll be readable, but the quadrillion people
who are using ChatGPT will be creating
[5:40] the exact same content.
[5:42] In fact, if I ask it to create a full 1,500-word
blog post based on the title we chose using
[5:49] the outline that was generated, and the
use cases I agreed with, it returns this.
[5:54] Like I said, it's readable
and still crazy impressive.
[5:59] But what exactly are we impressed by?
[6:02] For me, it's the fact that AI is able to stay
topically relevant, complete well-structured
[6:07] sentences, and in some
cases, write better than me.
[6:11] Where it falls short is 
the actual content itself.
[6:15] It's clear there's no expertise and there's
no way this content would actually satisfy
[6:21] people's intent for clicking through to
a ChatGPT use cases for SEO post.
[6:27] And if you think that writing content paragraph
by paragraph would be better, you would be right.
[6:33] But it doesn't change the fact that expertise
is lacking, and therefore, the content is just
[6:39] a bunch of rambling about nothing.
[6:42] Now, I do think that AI has its
place in content generation.
[6:45] And from my experience, it's mostly with
short-form content like meta descriptions.
[6:51] For example, I ran a crawl for our website
and it turns out we have around 300 pages
[6:56] with missing meta descriptions.
[6:58] So if I want a meta description for this page
on how to use Ahrefs' Keywords Explorer,
[7:03] I can ask ChatGPT: "Write a meta description
that's no more than 156 characters for a page
[7:09] titled: "How to use Ahrefs' Keywords Explorer."
[7:13] And that's good enough for me!
[7:15] Now, another consistently good use
case for ChatGPT is proofreading.
[7:20] For example, last year, we tested the quality
of freelance writers based on their rate.
[7:25] And the cheapest writer we worked
with charged us just $0.02/word.
[7:30] Now, if we take a part of the $0.02/word
post  and ask ChatGPT to proofread it,
[7:35] then in seconds, it makes small
but accurate improvements.
[7:40] Beyond proofreading, ChatGPT is pretty
good at writing extremely concise sentences
[7:46] to improve clarity in your content –
which I think is super underrated.
[7:51] In fact, you can use this to optimize
your pages for features snippets.
[7:55] For example, let's say that I'm looking
through our blog's keyword rankings
[7:58] and notice that we're not ranking for the
featured snippet "301 vs. 302 redirect."
[8:04] I can ask ChatGPT a question like,
"what's the main difference between
[8:08] a 301 and 302 redirect?"
[8:11] To which it gives a decent response.
[8:14] But it's not exactly optimized
for a featured snippet.
[8:17] Looking at the actual featured snippet itself,
I've made some mental notes to take back
[8:21] to ChatGPT to improve our chances
of taking over that snippet.
[8:26] I'll ask it to be more concise and to start
the sentence off with "The main difference"
[8:31] to directly address the query
"301 vs. 302 redirect".
[8:36] This is definitely more concise and it starts
with "the main difference" just as I asked.
[8:42] But this information is kind of incorrect
because there's a bit of nuance to how
[8:48] 301s and 302s pass link equity – which
again is why you shouldn't rely on any GPT
[8:55] to write full content or content
that requires expertise for you.
[9:00] This brings us to another bad use case of
ChatGPT which surprisingly a lot of SEOs
[9:06] are raving about – and that's
search intent classification.
[9:10] Now, you might be able to look at a keyword
like "how to tie a tie" and immediately know
[9:14] that the search results will
be dominantly informational.
[9:18] But doing it at scale, especially for keywords
with less context is a very different story.
[9:25] In order to identify search intent, you need
to actually look at the SERP, the top-ranking
[9:30] pages' content and things like SERP features to
come to a reasonable conclusion on intent class.
[9:37] But as far as I'm aware,
ChatGPT doesn't have SERP data.
[9:42] So check this out.
[9:43] Several months ago, Patrick, Josh,
and I picked five random keywords
[9:48] and attempted to assign an
'intent bucket' to the keywords.
[9:51] And as you can see, we had slightly
different opinions on each keyword.
[9:56] But we all chose the same dominant intent.
[10:00] When I put ChatGPT to the test, it did okay and
scored three out of five for the same keywords.
[10:07] But because it can't look at SERPs for these
keywords, it doesn't realize that an acronym
[10:11] like "AMA" which has multiple
meanings is navigational.
[10:16] And the same goes for "crockpot."
[10:18] In fact, it's horrible at identifying
navigational queries.
[10:22] And forget about keywords with local intent.
[10:25] If you can't trust its suggestions, you're
going to end up checking SERPs anyway,
[10:30] as you should, so there's no point in using
ChatGPT for this somewhat trivial task.
[10:38] But what it's really good at doing is
whipping up quick snippets of code
[10:41] for things like Schema markup,
and hreflang snippets.
[10:46] Now, you should have a good idea of some
effective ways to use ChatGPT for SEO and
[10:51] some things you may not
want to waste your time on.
[10:54] Here's a full list of the ChatGPT
use cases that we went through.
[10:57] Take a screenshot, try these prompts for
your own site, and subscribe to meet again
[11:02] in the next tutorial.

本文档为站内渲染。原始文件本地路径：saas/source/knowledge-people/Knowledge-World-人物-seo方法论-youtube-seo-scripts-ahrefs-scripts-0177b1.txt（仅本地保留，不入库不部署）