Lazarina Stoy - How to incorporate machine learning into your SEO day-to-day

Lazarina Stoy. Founder of MLforSEO, Marketing Consultant How to incorporate
ML into your SEO day-to-day A bit of ML theory, and a quickfire of ideas to implement ML in your daily routine (with templates ✨) October 17 - 18 2024 CAM Raleigh 409 W. Martin Street Raleigh, NC 27603

01 - What you really need to start 02 -
Where you can implement ML APIs straight away, instantly We’ll cover… 03 - What you need to grow 🌱 How to incorporate ML into your SEO day-to-day

@lazarinastoy | #techseoconnect 01. What you really need to start

@lazarinastoy | #techseoconnect

Here’s what you really need

@lazarinastoy | #techseoconnect To know • When to search for
ML • What model to use • How to find suitable ML tools • What you can achieve in a short time-frame • How to drive value via ML

@lazarinastoy | #techseoconnect Let’s start with the basics. For each
potential project consider three aspects.

@lazarinastoy | #techseoconnect task data solution Characteristics of

www.mlforseo.com Task characteristics

@lazarinastoy | #techseoconnect ML Supervised Unsupervised Clustering Dimensionality reduction Regression
Classification

@lazarinastoy | #techseoconnect ML You have labelled data to validate
results You don’t have a way to validate results Find patterns and group based on similarity Simplify or transform your data Make predictions Split into groups, based on existing classes

@lazarinastoy | #techseoconnect Needless to say, this is a very
simplified view.

www.mlforseo.com

Also…

@lazarinastoy | #techseoconnect Self-Train A machine learning model you train
from scratch, with your own data. Pre-Train А machine learning model that a third-party has trained. Fine-Tune А machine learning model that a third-party has trained, that you retrain, improve, adapt, fine-tune with your own data. You train the model further on a more specific dataset.

www.mlforseo.com Data characteristics

@lazarinastoy | #techseoconnect Is your input data… Textual? Numeric? Image-based?
Time series?

www.mlforseo.com Solution characteristics

@lazarinastoy | #techseoconnect Is this task mission critical? ✅ ❌
Don’t rely on AI. (seriously)

@lazarinastoy | #techseoconnect Do you need consistent results, every time?
✅ ❌ Avoid unsupervised ML. Avoid generative AI. Avoid deep learning. (yeah, really)

@lazarinastoy | #techseoconnect Do you need results to be easy
to understand? Do you need to explain them to stakeholders? ✅ ❌ Skip deep learning. (yes, that includes LLMs)

@lazarinastoy | #techseoconnect Is it okay that simply on average
the output outperforms existing methods? ✅ Okay, then. Take a look at ML options.

@lazarinastoy | #techseoconnect Assess usefulness of ML using multiple factors:
• insights • complexity • accuracy • scalability • assets (data in = data out) • resources • bottom line

How to find what you need whenever you have an
idea

Keep queries specific to data, task, and solution.

@lazarinastoy | #techseoconnect Writing meta descriptions Data Characteristics Textual Page
content Task characteristics Unsupervised • It is transformational (Page content to Page Summary in less than 160 characters) • It can also be generative (write them from scratch) Solution characteristics Mission critical? No Different results OK? Yes Explanation of process needed? Not really. Outperform current methods? Yes, much faster to get to a good enough result and satisfy a hygiene condition.

@lazarinastoy | #techseoconnect Title / H1 Optimisations Data Characteristics Textual
Page content Task characteristics Unsupervised • It is transformational (Page content to Page Summary in less than 60 characters) • It can also be generative (write them from scratch) Solution characteristics Mission critical? Could be, depending on the industry Different results OK? Could be critical for certain industries. Explanation of process needed? Sometimes. Outperform current methods? Yes, much faster to get to multiple first drafts, to pass onto an editor.

@lazarinastoy | #techseoconnect Image captioning/ Alt tag generation Data Characteristics
Image Image library Task characteristics Unsupervised Using a Pre-trained model image recognition model Generative AI / Image recognition Solution characteristics Mission critical? No Different results OK? Yes Explanation of process needed? Not really Outperform current methods? Yes, much faster.

@lazarinastoy | #techseoconnect 02. What to do for immediate value

@lazarinastoy | #techseoconnect Classification sorts data into specific categories using
a labeled dataset.

@lazarinastoy | #techseoconnect Quick check-in • Classification is a supervised
machine learning approach. • It involves sorting data (documents, pages, keywords) into pre-labeled categories • Applications include - content audit, competitor audit

@lazarinastoy | #techseoconnect With Google’s Natural Language API, you can
classify documents in 1,300+ predeﬁned categories

@lazarinastoy | #techseoconnect Process will take no more than 20
minutes

@lazarinastoy | #techseoconnect Create an API key

@lazarinastoy | #techseoconnect Identify content element to scrape

@lazarinastoy | #techseoconnect Scrape with 🐸

@lazarinastoy | #techseoconnect Enter your URLs and content

@lazarinastoy | #techseoconnect Run the script via a formula to
get classiﬁcation label & conﬁdence

www.mlforseo.com Plug-and-play template in Looker Studio

With Open AIʼs GPT4 or ChatGPT, results are a hit
or miss.

But why?

@lazarinastoy | #techseoconnect General purpose model Not efficient in large
datasets, Unreliable (unpredictable) results Non-replicable - output different every time, even if data doesn’t change. Generative AI, trained on a wide variety of general-purpose text but isn't fine-tuned on specific datasets for text classification unless explicitly prompted Great for creative outputs Purpose-built API, specifically designed for tasks like text classification, sentiment analysis, and entity recognition Efficient and reliable Output same every time, unless data changes. Pre-trained Supervised ML model, trained on vast amounts of labeled data related specifically to text classification tasks Great for tasks that require precision

www.mlforseo.com

@lazarinastoy | #techseoconnect Clustering is partitioning an unlabeled dataset into
groups of similar objects.

@lazarinastoy | #techseoconnect Watch the details later. Iʼve recorded a
step-by-step tutorial on doing topic modelling using a no-code, publicly-available, web-based app using LDA.

@lazarinastoy | #techseoconnect Topic models Topic models

@lazarinastoy | #techseoconnect Topic models Page Info

@lazarinastoy | #techseoconnect Identify content categories (classification) + topics +
subtopics Extract entities

@lazarinastoy | #techseoconnect • Interlink pages that mention the same
subtopic more than 30% • Interlink pages mentioning the same or semantically related entities • Improve content categories and tag systems

@lazarinastoy | #techseoconnect Great intro video for beginners

…but what you want to do is cluster keywords in
sheets

@lazarinastoy | #techseoconnect Process will take no more than 20
minutes

@lazarinastoy | #techseoconnect Run the script via the menu to
extract entities from content

@lazarinastoy | #techseoconnect Get entity data in seconds

@lazarinastoy | #techseoconnect Possible data points • Your content •
competitors’ content • Your competitors’ YouTube content • your SERP data versus competitors’ • ﬁrst-party data • UGC • social mentions • Your internal link text anchors …

www.mlforseo.com Does it matter how you do it?

Yes, use a tailored model. 53 16

GPT-4 vs. Google Cloud: Performance comparison on 9 SEO tasks

@lazarinastoy | #techseoconnect Fuzzy matching is a quick and dirty
way for calculating similarity between two strings

@lazarinastoy | #techseoconnect WATCH THE DETAILS LATER Iʼve recorded a
step-by-step tutorial on using fuzzy matching for things like: • Identifying link opportunities • String Similarity Analysis • redirect mapping of URLs

@lazarinastoy | #techseoconnect String similarity & redirect mapping

N-gram analysis: Understanding language used within the high-performing articles for
your terms can be beneficial for building content briefs.

A more advanced use case of n-grams and language analysis
to identify opportunities for Structured Data

@lazarinastoy | #techseoconnect Run the cell, paste the content Download
the output JSON From blog post

@lazarinastoy | #techseoconnect → Script tokenizes the text, discovers the
questions, and pulls the answers → Script organises these into a schema dictionary, which is saved as a JSON ﬁle

. The Content Moderation API module automatically analyzes text for
inappropriate or undesirable content, helping you to maintain a clean and professional data set without manually reviewing each entry.

But wait…

It can detect if a topic is YMYL 👀

@lazarinastoy | #techseoconnect Health Happiness Financial stability Safety

@lazarinastoy | #techseoconnect Possible data points • Your content •
Competitors’ content • YouTube video transcripts (monetization) • social media mentions • comments on your website • community posts …

www.mlforseo.com

@lazarinastoy | #techseoconnect Good videos on YouTube but not on
the blog? → Transcribe.

@lazarinastoy | #techseoconnect Approach Suitable for Limitation Tools No-code •
Beginners • Non-technical • Limited scalability Programmatic • Intermediate • A little bit more technical • API-savvy • Time • Adoption costs - learning, dev resources • Google Cloud Speech-to-Text • Amazon Transcribe • OpenAI Whisper - but bear in mind it sucks for anything over 2-3 minutes, and has no small language support.

Caveat

@lazarinastoy | #techseoconnect What I’m not saying ❌ What I
am saying ✅ • Spam your blog with auto-transcribed content • Fire your content team • Scrape competitorsʼ Youtube videos, transcribe, and traffic to the moon, bro 🥲 • Bridge gaps between different teams, if enterprise • Make content work harder, especially if youʼre already producing webinars, live streams, etc. • Use transcription for competitor analysis, not copying

Mix & match with other approaches 🌟

@lazarinastoy | #techseoconnect Scrape videos/audio Transcribe Context: • SERP Analysis
shows Google ranks more videos, but there is still lots of traffic for web pages. • There are some YouTubers that donʼt do a good job at blogging, but their channels get a ton of traction Identify topics + subtopics Extract entities • Compare with website • Add to topical map • Find and address information gaps

www.mlforseo.com

@lazarinastoy | #techseoconnect You have a library of high-performing tutorials
but no presence on YouTube/TikTok? →Scale production with text to speech.

Beginners • Non-technical • Limited scalability Programmatic • Intermediate • A little bit more technical • API-savvy • Time and other adoption costs • Google Cloud Text-to-Speech API • Amazon Polly - Text To Speech AI Tool • OpenAI GPT4o (soon)

@lazarinastoy | #techseoconnect What I’m not saying ❌ What I
am saying ✅ • Spam YouTube with AI generated trash • You can replace video production • Certain content formats donʼt require video and can be made more accessible via audio & stills, like interviews or tutorials • To add automation, but still have at least some personalised look/feel, tutorial videos might have avatars, instead of person-to-camera setups to lower costs

www.mlforseo.com

Beginners • Non-technical • Limited scalability • ChatGPT • Custom GPTs • Web tools (they’re all wrappers of GPT, so not worth it) Programmatic • Intermediate • A little bit more technical • API-savvy • Time and other adoption costs • GPT4/ GPT4o • Any LLMs • BERT

@lazarinastoy | #techseoconnect You have a library of high-performing blog
posts but no content distribution? →Transform blog posts to insightful posts for social media.

@lazarinastoy | #techseoconnect You have a library of high-performing blog
posts but no newsletter? →Use an LLM to rewrite these into newsletter edition drafts. You have comprehensive guides or reports in PDF format? →You can extract key insights, summaries, or actionable tips from these documents and repurpose them into blogs or social posts/ threads.

www.mlforseo.com Overall, any LLM would do a great job here.

While we’re on the topic of LLMs doing a good
job…

Structured data + LLMs = ♡

www.mlforseo.com

@lazarinastoy | #techseoconnect 03. What you need to grow 🌱

Mindset + Community + Resources

www.mlforseo.com

www.mlforseo.com ✧ academy.mlforseo.com ✧

Thank you for listening. ♡ Find my deck at lazarinastoy.com/conference-decks-and-
presentations/

Lazarina Stoy - How to incorporate machine lear...

Lazarina Stoy - How to incorporate machine learning into your SEO day-to-day

More Decks by Tech SEO Connect

Other Decks in Marketing & SEO

Featured

Transcript