The advent of Google's Search Generative Experience (SGE) is revolutionizing online search, ushering in a new era of contextualization and intuition in information discovery.
This technological advancement is fundamentally changing SEO strategies and requires professionals to adopt a new approach to content creation.
The impact on users is equally significant, with AI making search results much easier to access.
This article proposes an advanced thematic mapping approach to maximize the effectiveness of these technologies in SEO.
We will also cover knowledge of large-scale language models (LLMs) such as OpenAI's GPT, Google's Bard, and Microsoft's Bing AI, highlighting their limitations and potential in SEO content creation.
Introducing Google SGE
Google SGE marks a revolutionary change in online search. With this innovation, Google takes a more contextual and intuitive approach to information search.
This development has a major impact on how SEO professionals need to think and plan their content strategies.
The user experience is also changing as AI makes search results easier to find.
Get instant access to answers without having to navigate through multiple tabs or pages.
Understanding how this AI works and using new methods to extract that knowledge is essential to positioning ourselves effectively and understanding its limitations.
Understand large-scale language models (LLM)
LLMs such as GPT, Bard, and Bing AI are powerful tools with excellent natural language generation and understanding capabilities.
However, these models have limitations, especially when it comes to understanding specific contexts and updating information.
Image from author, January 2024SEO project staff must understand these limitations to maximize the efficiency of content creation.
There are two types of knowledge. One is the knowledge that comes from the data used for training, and the other is the knowledge that is in the search engine's index and is used as part of the answer.
To explain this, I would like to show how this knowledge can be mapped.
The importance of thematic mapping
Thematic mapping is an important tool in SEO that organizes and structures content in a logical and intuitive way.
This ensures that all aspects of the topic are covered and increases the relevance and quality of your content. He LLM for thematic mapping gives you a unique advantage in generating new ideas and perspectives.
Building a thematic map
Topic mapping is the practice of grouping related ideas and topics into clusters to facilitate the creation of coherent and comprehensive content.
This approach not only helps you organize your ideas logically, but also helps you identify gaps in your existing content.
Topic map architecture
Select topics and keywords
Choose a niche topic and identify relevant keywords. You can start with any LLM, but I prefer her one approach.
The first is to use Google's AI, such as PaLM 2, if you're comfortable with Google's tools (FYI, I've set up a training course at Data Marketing Labs).
A very simplified prompt to retrieve the ontology that exists in ChatGPT is:
- Please give me a list of ontology tables related to “your concept”.
ChatGPT 4, January 2024 screenshotbrainstorming
For each expression, ask your LLM to write and brainstorm several sentences related to that expression.
People often ask me why I create multiple passages. The answer is simply that depending on your creativity threshold and the answers in Google's index, your LLM answers can be slightly different, allowing you to include areas of possibility.
This is an illustration of PaLM 2 being used to generate topics that are fully recognized by AI and searched by web users. The more topics you request, the better the topics will be covered.
SGE simulator screenshot, January 2024extraction
Then you can extract all the entities mentioned in relation to the concept.
Initially I used a Python library, but now I can use LLM which is much easier to work with.
Eventually everything will be stored in an array and you can count the number of times a concept appears. I would like to explain this part in detail.
In this image you can see that we are running 5 generations for each previous topic to try to recover as many relevant elements as possible. This helps in generating mind maps.
For each generated text, important terms are extracted using PaLM 2, all of which are stored in a table.
PaLM 2, January 2024 screenshotAs you can see, each step is performed in Google Colab, providing a ready-to-use table and allowing you to easily sort the data with just a few clicks.
Google Colab screenshot, January 2024You can then create a thematic map from this prompt.
Screenshot by author, January 2024Possible outcomes are:
**Step 1: Create a topic map**
**Topic:** Bicycle
**Noun/Predicate:**
**1. Type of bicycle**
– Peloton Bike
– Electric bicycle
– Mountain bike
– road bike
**2. Bicycle components**
– Sound Bike Boy Bell
– bike clip
– bicycle pedals
– Road bike pedals
**3. Bicycle activities**
– Run your walking bike regularly
– Motorcycles fully recognized by humans
**4. Bike accessories**
– Mountain bike tires
**5. Bicycle safety**
**Step 2: Semantic Graph**
| Subtopic 1 | Subtopic 2 | Semantic Connections |
|—|—|—|
| Peloton Bike | Electric Bicycle | Both are types of bicycles that run on electricity. |
| Electric Bicycle | Sound Bike Boy Bell | Both are components that can be added to your bike. |
| Sound Bike Boy Bell | A bicycle that fully recognizes humans | Both are related to rider safety. |
| A fully human-aware bicycle | Performs a regular walking bike. Both are related to the physical activity of riding a bicycle. |
| Run a walk bike regularly. Mountain Bike Tires | Mountain Bike Tires Both relate to the terrain the bike can ride on. |
| Mountain Bike Tires | Mountain Bike Tires Road Bike Pedals | Both are components that can be added to your bike. |
| Road bike pedals | Bike clip | Both are components that can be added to your bike. |
**Step 3: Mind Map**
**Topic:** Bicycle
**Subcategory:**
1. Types of bicycles
– Peloton Bike
– Electric bicycle
– Mountain bike
– road bike
– BMX bike
2. Bicycle components
– Sound Bike Boy Bell
– bike clip
– bicycle pedals
– Road bike pedals
– bike seat
3. Bicycle activities
– Run your walking bike regularly
– Motorcycles fully recognized by humans
– Bicycle racing
– Bike touring
– Commuting by bicycle
4. Bicycle accessories
– Mountain bike tires
– bike helmet
– Bicycle light
– Bicycle pump
– bike rack
5. Bicycle safety
– Bicycle brakes
– Bicycle reflector
– Bicycle lock
– Bicycle insurance
– Bike maintenance
6. Bicycle brand
– specialized
– Trek
– Giant
– Cannondale
– Scott
7. Bike shop
– spirit
– performance bike
– Dicks Sporting Goods
– Walmart
– the goal
8. Bike event
– Tour de France
– Giro d’Italia
– Vuelta a España
– California Tour
– United States Cycling Championships
9. Bike club
– Federation of American Bicyclists
– Sierra Club
– National Bike Club
– Adventure Cycling Association
– Bikers against child abuse
10. Bicycle advocacy
– People who love bikes
– Rails-to-Trails Conservation Group
– Bike Walk Alliance
– National Safe School Routes Center
– International Bicycle Fund
Visualization
You can visualize the whole thing using mind mapping tools, and the results can be very informative.
For easy visualization, ChatGPT has a free assistant called AI Diagrams.
Please try searching. You can then request mind map generation from the table in the previous step.
ChatGPT 4, January 2024 screenshot
ChatGPT 4, January 2024 screenshotHere, I would like to suggest some advanced actions with an eye toward Google SGE.
Google SGE advanced strategies
- Use Google's PaLM 2 to ensure your map covers all aspects of your topic.
- Integrate maps into your content research and writing process.
- Convert each subtheme into a web page, blog post, or other form of content and link them to create an interconnected web of content.
This methodology provides a robust way to understand the role of generative AI in search engines and optimize generative AI search capabilities.
Filled with detailed examples and explanations, it focuses not only on topic optimization, but also on prioritizing content quality and targeting specific search intent.
Human intervention remains important for search intent and content quality.
By combining skilled writers with AI, you can enhance content optimization with tools that maximize the efficiency and relevance of your ecosystem.
The advent of generative AI will allow any SEO professional to build their own tools.
Other resources:
Featured image: Summit Art Creations/Shutterstock
