In layman’s terms, we can define topically relevant content as a group of assets (blog posts, webinars, podcasts, faqs) that cover in-depth a specific area of expertise. In reality, though, there are various challenges in compiling this list:<\/p>\r\n\r\n\r\n\r\n
- we want to identify all the themes and subthemes<\/strong> related to a given concept;<\/li>
- we want to do it by using the various formats<\/strong> that we use (content from our academy, blog posts, and ideally content that we might have published elsewhere);<\/li>
- we need to keep in mind different personas<\/strong> (the SEO agency, the in-house SEO teams of a large corporation, the bloggers, etc.). <\/li><\/ul>\r\n\r\n\r\n\r\n
In this article, I will share how you can build content hubs by leveraging deep learning<\/strong> and data in a knowledge graph. We will use specifically a technique called knowledge<\/strong> graph embeddings<\/a> <\/strong>(or simply KGE). This is an approach to transform the nodes and edges (entities and relationships) in a low dimensional vector space that fully preserves the knowledge graph’s structure.<\/p>\r\n\r\n\r\n\r\n
<\/a> Here is the link to the Colab<\/a> that will generate the embeddings.<\/p>\r\n\r\n\r\n\r\n
<\/a> Here is the link to the TensorFlow Projector<\/a> to visualize the embeddings.<\/p>\r\n\r\n\r\n\r\n
<\/p>\r\n\r\n\r\n\r\n
Let\u2019s first review a few concepts together to make sure we\u2019re on the same page.<\/p>\r\n\r\n\r\n\r\n
<\/p>\r\n\r\n\r\n\r\n
- What is a content hub?<\/a><\/li>
- What is a knowledge graph in SEO?<\/a>
- Our dataset: the KG of this blog<\/a><\/li><\/ul><\/li>
- What are knowledge graph embeddings (KGE)?<\/a><\/li>
- Let\u2019s build the knowledge graph embeddings<\/a>
- Model evaluation<\/a><\/li><\/ul><\/li>
- How to create a content hub<\/a>
- Let\u2019s start predicting new facts<\/a><\/li>
- Exploring embeddings to discover sub-topics and relationships<\/a>
- Let\u2019s review the concept of Semantic SEO<\/a><\/li>
- Let\u2019s explore Structured Data<\/a><\/li>
- Topic Clustering<\/a><\/li><\/ul><\/li><\/ul><\/li>
- Conclusion<\/a>
- More questions on Content Hubs<\/a>
- Why are content hubs important in Semantic SEO?<\/a><\/li><\/ul><\/li>
- References<\/a><\/li><\/ul><\/li><\/ul>\r\n\r\n\r\n\r\n
What Is A Content Hub?<\/h2>\r\n\r\n\r\n\r\n
A content hub<\/a> is where you want your audience to land after triggering a search engine’s broad search query. A content hub is presented to the user either as a long-form article<\/em> or as a compact category page (<\/em>Content Harmony here<\/a> has a nice list of various types of content hubs)<\/em>. In both cases, it needs to cover the core aspects of that topic. <\/p>\r\n\r\n\r\n\r\n
The content being presented is not limited to what we have on our site but should ideally include assets that have been already developed elsewhere, the contributions of relevant influencers, and everything we have that can be helpful for our audience. <\/p>\r\n\r\n\r\n\r\n
Experts and influencers in the given subject\u2019s field have a strategic role in establishing the required E-A-T (Expertise, Authoritativeness, and Trustworthiness) for each cluster.<\/p>\r\n\r\n\r\n\r\n
What Is A Knowledge Graph In Seo?<\/h2>\r\n\r\n\r\n\r\n
A knowledge graph is a graph-shaped database made of facts: a knowledge graph for SEO<\/a> describes the content that we produce so that search engines can better understand it. <\/p>\r\n\r\n\r\n\r\n
Our Dataset: The Knowledge Graph Of This Blog<\/h3>\r\n\r\n\r\n\r\n
In today\u2019s experiment, we will use the Knowledge Graph behind this blog to help us create the content hubs. You can use any knowledge graph as long as it describes the content of your website (using RDF\/XML or even a plain simple CSV).<\/p>\r\n\r\n\r\n\r\n
![\"\"](\"https:\/\/wordlift.io\/blog\/en\/wp-content\/uploads\/sites\/3\/2021\/11\/Schermata-2021-11-15-alle-18.55.24.png\")
<\/figure>\r\n\r\n\r\n\r\nIn most essential terms, a graph built using WordLift connects articles with relevant concepts using semantic annotations. <\/p>\r\n\r\n\r\n\r\n
There is more, of course, some entities that can be connected to each other with typed relationships; for example, a person (i.e. Jason Barnard<\/em>) can be affiliated<\/em> with an organization (Kalicube<\/em>) and so on depending on the underlying content model<\/a> used to describe the content of the site. <\/p>\r\n\r\n\r\n\r\n
Here below, we see a quick snapshot of the classes that we have in our dataset. <\/p>\r\n\r\n\r\n\r\n
<\/p>\r\n\r\n\r\n\r\n
What Are Knowledge Graph Embeddings (KGE)?<\/h2>\r\n\r\n\r\n\r\n
Graph embeddings<\/strong> convert entities and relationships in a knowledge graph to numerical vectors and are ideal for \u201cfuzzy\u201d matches. Imagine graph embeddings as the fastest way to make decisions using the Knowledge Graph of your website. Graph embeddings are also helpful to unveil hidden patterns in our content<\/strong> and cluster content into groups<\/strong> and subgroups.<\/p>\r\n\r\n\r\n\r\n
<\/p>\r\n\r\n\r\n\r\n
Deep learning and knowledge graphs are in general complex and not easy to be visualized, but things have changed, and we can now easily visualize concepts in high-dimensional vector spaces using Google\u2019s technologies like TensorBoard. Meanings are multi-dimensional as much as people are. The magic of embeddings lies in their ability to describe these multiple meanings in numbers so that a computer can \u201cunderstand\u201d them. <\/p>\r\n\r\n\r\n\r\n
We can approach a given concept like \u201cSemantic SEO\u201d from so many different angles. We want to use machine learning to detect these angles and group them in terms of assets (content pieces) and entities (concepts). <\/p>\r\n\r\n\r\n\r\n
Let\u2019s watch a video to grasp more about clustering topics, as this is what we\u2019re about to do. <\/p>\r\n\r\n\r\n\r\n
- References<\/a><\/li><\/ul><\/li><\/ul>\r\n\r\n\r\n\r\n
- Why are content hubs important in Semantic SEO?<\/a><\/li><\/ul><\/li>
- Let\u2019s explore Structured Data<\/a><\/li>
- Exploring embeddings to discover sub-topics and relationships<\/a>
- How to create a content hub<\/a>
- What are knowledge graph embeddings (KGE)?<\/a><\/li>
- What is a knowledge graph in SEO?<\/a>
- we want to do it by using the various formats<\/strong> that we use (content from our academy, blog posts, and ideally content that we might have published elsewhere);<\/li>