🧵 𝗘𝗺𝗯𝗲𝗱𝗱𝗶𝗻𝗴𝘀 & 𝗦𝗘𝗢: A Powerful Multitool 🛠️

In the world of #SEO, understanding and leveraging the power of #embeddings is a game-changer. But what are embeddings, and how do they work? Can we build our embeddings?

Let's dive in! #AI #Semantics

1/9 𝗪𝗵𝗮𝘁 𝗮𝗿𝗲 𝗪𝗼𝗿𝗱 𝗘𝗺𝗯𝗲𝗱𝗱𝗶𝗻𝗴𝘀? 📚
Word embeddings are a type of word representation that allows words with similar meanings to have a similar representation in a multi-dimensional space. Using embeddings, we convert words into math (numerical vectors).

2/9

🎺New Article on Neuro-Symbolic AI and #SEO🎺

💡 Neuro-Symbolic AI is a way to combine the power of knowledge graphs with deep learning techniques using *Retrieval Augmented Generation*.

🔗 Article: wordlift.io/blog/en/neuro-…
💬 AskMe: a widget inside the article

1/4 🧵 💬 AskMe is the first experiment to let readers "talk" with the article's author and ask questions.

⚠️ It is a WIP and requires your patience 🐌

It has been developed by the wonderful @wordliftit team using the KG behind the blog, @llama_index, @LangChainAI and @JinaAI_

2/4

I worked on my first experiment with ChatGPT Plugins applied to SEO! I created a search engine for an eCommerce site using WordLift's Product Knowledge Graph (PKG) as a starting point. Here is what I learned:

#SEO #ChatGPT #WordLift #eCommerce

🧵 1/6 1. You can use @LangChainAI to experiment with the idea (here is the documentation 📖: python.langchain.com/en/latest/modu…) and choose any of the supported LLM. #Opensource is amazing 🤩.

2. You only need two files: a JSON manifest and the OpenAPI specs.

2/6

📢 AI-assisted Alt Text for Images 🪄✨

🧵Image SEO has tremendous potentials as AI-powered technologies make search more visual and intuitive.

✅ wordlift.io/blog/en/image-… [blog post]
🤖 wor.ai/image-captioni… [Colab]

Interested in automatic captioning? This is for you

1/ Google has recently updated the Image SEO best practices, and if you missed it, I suggest you start from @RoxanaStingu's update:

https://twitter.com/RoxanaStingu/status/1620738018742239232?ref_src=twsrc%5Etfw%7Ctwcamp%5Etweetembed%7Ctwterm%5E1620738018742239232%7Ctwgr%5E93aebe6d82f62d2d85b75d61a83e4e0256abee45%7Ctwcon%5Es1_&ref_url=https%3A%2F%2Fwordlift.io%2Fblog%2Fen%2Fimage-seo-using-ai%2F

I have worked on automatic image captioning since 2019; recently, I have done a new analysis of the SOTA.

2/

A small thread about Semantic SEO and #ChatGPT 🪡

As @SilviaKaya22 was testing @wordliftit new version of the SEO Add-on for Google Sheets™, she quickly compared @aleyda and me 😳.

1/7 I feel like a newbie and an apprentice compared to Aleyda; nevertheless, the results grabbed my attention.

Using the new Add-on, we can compare search queries (and URLs) by looking at the entities behind top search results (or the entities behind single or multiple URLs).

2/7

This is great, and here is what you can do with it 🧵:

1. Blend structured data with metrics from Google Search Console 🔀(or any other source).

2. Evaluate clicks performance for each schema type
(including types like schema:service that we currently don't have in GSC).

1/5

https://twitter.com/ziodave/status/1543966952464547842

3. Filter data by entity (or topic). Make sure to activate the Chart cross-filtering option to turn any chart into an interactive filter.

2/5

A new SEO workflow for e-commerce sites. In this tutorial, we will create internal links on PLP

1⃣ Extract text using #advertools 🕷️
2⃣ Get queries from GSC
3⃣ Compute Similarity
4⃣ Add semantic markup

- wordlift.io/blog/en/intern… [blog post✍️]
- bit.ly/3aRvN4o [code🐍] I worked on the @FILAUSA website (not a client of ours) that currently doesn't have a related search widget.

To build one, we will index 'title', 'meta description', 'intro text' and 'breadcrumbs' and use the title of any other PLP as 'query'.

💎 New blog post on #ContentHub for #Semantic #SEO. How to cluster content using Knowledge Graph Embeddings to detect:

✓ Clusters
✓ Sub-topics
✓ Author's topical authority

🖋️ Post
🐍 Colab https://t.co/JlZJb2Wn50
📽 Embeddings https://t.co/PtDvk73yARwordlift.io/blog/en/conten…
bit.ly/topic-hubs
bit.ly/KG-embeddings 1/

We can train a model with @TensorFlow to reveal our content's hidden patterns and cluster them into subgroups. In this experiment, I used data from WordLift's blog and a library called #AmpliGraph by @lukostaz.