Patent Lifts the Curtain on Massive 2018 Core Algorithm Update
Could we finally know the secret behind one of Google’s biggest algorithm update in recent years? Potentially. A recent patent published by Google has given us a glimpse behind the curtain of the infamous E-A-T update. The patent, which was officially published on February 13, 2020, is titled Website Representation Vector to Generate Search Results and Classify Website – try saying that three times fast! Essentially, the patent describes how Google is able to classify websites depending on whether they meet thresholds based upon quality scores, and then use that classification to assign different weights to rankings. https://twitter.com/bill_slawski/status/1231410913560821760 The patent document goes on to say the quality scores may be specific for a particular knowledge domain, and lists the following as examples of knowledge domains: [su_list icon=”icon: chevron-right” icon_color=”41bf60″]
- Artificial intelligence
[/su_list] Here is a snippet of the patent: “Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using website representations to generate, store, or both, search results. One of the methods includes receiving data representing each website in a first plurality of websites associated with a first knowledge domain of a plurality of knowledge domains and having a first classification; receiving data representing each website in a second plurality of websites associated with the first knowledge domain and having a second classification; generating a first composite-representation of the first plurality of websites; generating a second composite-representation of the second plurality of websites; receiving a representation of a third website; determining a first difference measure between the first composite-representation and the representation; determining a second difference measure between the second composite-representation and the representation; and based on the first difference measure and the second difference measure, classifying the third website.”
So, What Does This Have to Do With E-A-T?
Considering the range of industries covered under the patent – and the fact that it was filed the same week as the update – this could explain a lot about the August 2018 E-A-T update. To refresh your memory, E-A-T (which stands for expertise, authority, and trust) was a massive core algorithm update nicknamed the “medic” update due to its significant affect on medical websites. In fact, it’s estimated that over 41% of all websites affected by the update were related to the health/medical industry. The main focus of the update was to favour sites that are able to prove they have credibility, expertise, trust, and authority related to the topics they covered, particularly when it comes to health, finance, or e-commerce websites. Essentially, this patent gives us a look into how Google is able to determine the category of a particular website and therefore understand if the site should have a certain level of authority behind it. The patent reads:
“For instance, the website classifications may include a first category of websites authored by experts in the knowledge domain, e.g., doctors, a second category of websites authored by apprentices in the knowledge domain, e.g., medical students, and a third category of websites authored by laypersons in the knowledge domain.”
Between the contents of the patent and the fact that it was filed the same week that E-A-T rolled out, it’s fair to say that the two are most likely related. However, it should be noted just because Google has this patent, doesn’t necessarily mean it’s actually being put to use. But if it is being used, this definitely sheds a bit of light on the always so mysterious Google algorithm updates. Especially considering the fact that we’re usually left in the dark regarding these kinds of updates and aren’t aware that they’re happening until rankings start to fluctuate.