Google patent application reveals insights into E-A-T and health site categorization
Google recently published a new patent application that was originally filed on August 10, 2018. The patent is named "Website Representation Vector to Generate Search Results and Classify Websites." Bill Slawski was the first to cover this new patent and did an outstanding job simplifying its content.
The abstract: The abstract, although technical, explains how Google can classify a website into multiple categories. Here is the abstract:
“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.”
What does this mean? According to Slawski, the patent application uses Neural Networks to understand patterns and features behind websites to classify those sites. This classification system refers to “a composite-representation, e.g., vector, for a website classification within a particular knowledge domain.” These knowledge domains can include topics such as health, finance, and more. Sites classified within specific knowledge domains may have an advantage in returning search results in response to search queries.
In essence, it seems Google can determine the category of a site and assess whether the site has a certain level of authority. Is the site written by experts, and does it have authority? The patent states, “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.”
E-A-T: This concept rings true with E-A-T (Expertise, Authoritativeness, and Trustworthiness) from Google’s search quality raters guidelines. Unlike the guidelines, this patent application could be used to create ranking signals and algorithms.
Timing of this: The timing of this patent application’s release is also noteworthy. It was published in August 2018, around the time of the August 1st core update, nicknamed the Medic Update, which appeared to focus significantly on health and medical sites. The patent application contains numerous references to health, medical, doctors, and related terms.
More: Remember a year ago, a white paper released by Google mentioned they might use different ranking weights for YMYL (Your Money or Your Life) queries? This patent aligns with how Google might manage this. If Google can classify different sites as part of the YMYL areas, then it can emphasize expertise, authority, and trustworthiness more, as described in the patent application.
Why we care: SEOs enjoy debating, and this recently published patent might provide more insight into theories around the August 1st update and whether Google can measure E-A-T or classify YMYL sites. However, keep in mind that Google has repeatedly stated that holding a patent does not necessarily mean it is being used.
