Automating content optimisation with the help of semantic value

@frankvndijk

@frankvndijk Friday 11:10am, where two worlds collide

Perfect, because what I'm about to tell you is technical...

@frankvndijk

@frankvndijk What are embeddings? “Embeddings are numerical representations of data
(like words, images, or audio) in a multi- dimensional space” Images Audio Text Embedding model 0.9 0.7 0.2 0.6

@frankvndijk cat Embedding model 0.9 0.7 -0.3 0.6

@frankvndijk cat dog 0.9 0.7 -0.3 0.6 0.9 0.6 -0.2
0.8

@frankvndijk cat dog lion

@frankvndijk It’s not that difficult!

@frankvndijk Text-embedding-3-large By OpenAI, highest performance but more expensive Text-embedding-3-small
By OpenAI, excellent performance and lower cost Gemini-embedding-001 By Google, flexible in use with dimensions Comparison of different models

@frankvndijk Introducing EmbeddingGemma Open source Privacy Small but very powerful

@frankvndijk Big websites ask for creativity Comparing 1k+ urls in
a content gap… No way 🫠

@frankvndijk I mean... It shows you interesting keywords, but not
the whole picture Content gap 🫤

@frankvndijk Try Plotly for your visualisations Free Python package Interactive
data showcase Web app integrated

@frankvndijk

@frankvndijk Organic traffic data Vector embeddings Competitor & own urls

@frankvndijk API Access >> Ahrefs + Gemini API connection

@frankvndijk Ahrefs >> Backlinks, RefDomains, URL Rating off and Traffic
on Gemini >> Extract embeddings from page content Right settings

@frankvndijk Extraction >> Store rendered HTML Rendering >> JavaScript Rendering
on

@frankvndijk Export to graph with Python

@frankvndijk

@frankvndijk Perfect showcase of the right data Show your strengths
Show optimization options Makes it visual for non SEO

@frankvndijk

@frankvndijk Enable embedding functionality, semantic similarity and low relevance Connect
to your embedding template With embeddings

@frankvndijk 0 1 Identical No similarity Cosine similarity

@frankvndijk Try a threshold of 0.8 Crawl to find new
internal links

@frankvndijk Similar pages will show up Source url Target url

@frankvndijk Workflow to find non existing links Inlinks Semantically similar

@frankvndijk Try it yourself, there is a QR code at
the end

@frankvndijk Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed
do eiusmod tempor incididunt ut labore et dolore magna aliqua. Audit anchors with cosine similarity 0.9 0.7 -0.3 0.6 0.9 0.6 -0.2 0.8

@frankvndijk Finding irrelevant anchors Inlinks Embeddings

@frankvndijk Vector embeddings are so interesting because… Google has been
using them for years

@frankvndijk Retrieval Augmented Generation Identify Retrieve information Generate AI

@frankvndijk We need to check what content is used to
generate the AI overview +more sources

@frankvndijk How good is their content based on a semantic
level +more sources 0.81 0.77 0.83

@frankvndijk Should we optimize for a cosine similarity of 1.0?

@frankvndijk Don’t forget your SEO It’s the foundation of a
successful GEO strategy. Without a strong SEO base, your GEO strategy will fail

@frankvndijk Success is no longer just about matching a query,
it’s about deeply understanding the intent and the questions behind it, and answering them

@frankvndijk PHASE 1 PHASE 2 PHASE 3 PHASE 4 PHASE
5 Find relevant queries Extracting content Generate embeddings Calculating (cosine) similarity Optimizing content

@frankvndijk Start by finding the full search intent Get insights
from:

@frankvndijk We can take a look behind the scenes at
the competition with Ahrefs

@frankvndijk Use regex to filter out long tail keywords that
might be relevant to your query

@frankvndijk Or check what ChatGPT is using to find information
to generate an answer Great tip from Mark Williams-Cook

@frankvndijk All these insights give us a better insight of
what our target audience is looking for SERP features like people also ask, people also search for Insights from Gemini Trends from Google Trends

@frankvndijk Extract the right content to compare Get the content
by using:

@frankvndijk We need to scrape the content that is used
in the AI overviews

@frankvndijk Chunk your own content so we can use it
check if it’s good (enough)

@frankvndijk Start my finding the full search intent 0.9 0.7
-0.3 0.6 0.9 0.6 -0.2 0.8

@frankvndijk Sorry… It was an workflow all along… Sorry not
sorry…

@frankvndijk Please don’t start keyword stuffing now…

@frankvndijk Start adding value instead

@frankvndijk Script that checks relevancy of backlinks based on Ahrefs
export DR + relevancy

@frankvndijk What’s next Start calculating cosine similarity Switch from search
query to intent Start automating with the Google Sheets 01. 02. 03.

@frankvndijk Your [SEO/GEO/AEO] strategy should still draw the map and
set the destination, let vector embeddings be the compass that guides you throughout the journey

55 DEPT®/SEO Brein | @frankvndijk Thank you for listening :)

Automating content optimisation with the help o...

Automating content optimisation with the help of semantic value

More Decks by Frank van Dijk

Other Decks in Marketing & SEO

Featured

Transcript