O'Reilly logo
live online training icon Live Online training

Artificial Intelligence for SEO

AI and Machine Learning for SEO automation

Andrea Volpini

With advancements in artificial intelligence happening everyday and Google pushing search results into the realm of natural conversation, understanding how machine learning and natural language processing can be applied to Search Engine Optimization (SEO) is of high value for marketeers, SEOs and content creators. We will use practical examples using Python and Google Colab to demonstrate the advantages of deep learning for spotting new opportunities in search results, for scaling our content marketing operations and for learning how artificial intelligence is transforming search and – what we shall do about it.

What you'll learn-and how you can apply it

By the end of this live, hands-on, online course, you’ll understand:

  • The differences between AI, machine learning and deep learning
  • Elements of natural language processing and word embeddings
  • Leveraging both human and machine intelligence to create machine learning models and workflow: the human-in-the-loop approach applied to SEO
  • Data preparation for machine learning projects

And you’ll be able to:

  • Automate the summarization of articles to generate the meta description tags
  • Analyze the SERP using natural language processing for entity extraction
  • Improve your titles by comparing the distance with the most relevant query using word vectors

This training course is for you because...

  • You’re an SEO, marketer or content writer willing to use machine learning in your approach
  • You work with content and data to increase traffic on your website
  • You want to improve your SEO skills by understanding more about applied artificial intelligence


  • General understanding of SEO
  • Basic understanding of general programming (the session will use Python and Google Colab)

Recommended preparation:

  • An account on Google Colab is needed to complete the course exercises

Recommended follow-up:

About your instructor

  • Andrea Volpini, CEO of WordLift, works on the intersection between semantic web, artificial intelligence and search engine optimization helping brands worldwide to increase their organic search visibility, traffic and conversions.

    Andrea has 20+ years of world-class experience in digital marketing. Co-founder of InSideOut10, in 2013 Andrea Volpini also kick-started RedLink, a research spin-off focusing on artificial intelligence, and information extraction.


The timeframes are only estimates and may vary according to how the class is progressing

1 - Don’t believe the hype and start using AI for SEO (60 minutes)

  • Lecture (20 minutes): Artificial intelligence (AI), machine learning (ML) and deep learning: how they are different and why business fail in using them; differences between AI research and applied AI; the importance of high quality (semantic) data for your ML projects.
  • Group discussion & Polls (10 minutes)
  • Hands-on exercise (10 minutes): Using text summarization to reduce the time required for writing meta descriptions on large websites.
  • Wrap-up, Q&As and Take-Aways (10 minutes)
  • Break (10 minutes)

2 - Understanding Google SERP using Natural Language Processing (60 minutes)

  • Lecture (20 minutes): How NLP can help us interpret textual content at scale, extracting entities and an introduction to Linked (Open) Data and the Google Knowledge Graph.
  • Group discussion & Polls (10 minutes)
  • Hands-on exercise (10 minutes): Using NLP and named-entity extraction to analyze Google search results pages.
  • Wrap-up, Q&As and Take-Aways (10 minutes)
  • Break (10 minutes)

3 - Why do we need embeddings and how we can use them to improve organic CTR? (60 minutes)

  • Lecture (20 minutes): Introduction to TensorFlow, Embeddings and the Encoder-Decoder architecture; preparing to use the Universal Sentence Encoder to evaluate the semantic distance between queries and titles.
  • Hands-on exercise (20 minutes): TF-Hub and the Universal Sentence Encoder in action; understanding patterns in the resulting data using Google FACETS .
  • Wrap-up, Q&As and Take-Aways (10 minutes)
  • Break (10 minutes)