BERT: learn about the new Google algorithm and how it works

It is possible that you have not yet heard of BERT, Google’s new artificial intelligence system, but it is expected that it will soon affect the results of many of the searches carried out and therefore the online strategy of your business.

With some frequency, Google implements certain changes in its search system. Some of them are subtle, while others have already put the world of SEO and upside down.

Now the company is preparing its biggest innovation in the last five years, the biggest since the introduction of RankBrain. It is estimated that the new algorithm will affect 1 out of 10 results pagesdrastically altering the pages that rank in these searches.

The BERT was launched at the end of October this year for searches in English and will soon start to work in other languages.

Continue reading this article to learn more details about BERT, how it works, its impact on the SERP and what will be the biggest changes implemented in the from now on.

What is Google BERT and how does it work?

BERT is an acronym for Bidirectional Encoder Representations from Transformers. The name seems complicated, but the concept is simple to understand.

It is a neural network technology created to improve natural language processing. In other words, it helps Google robots to understand language in a way that is more similar to how we humans do.

Currently, the platform uses an indexing and tracking system that basically considers the used by the user. However, with the BERT Google starts to also consider the sequence and the context of the sentence.

To make it easier to understand:

The current model basically looks at the order of the terms in the phrase that the user used to perform a search. With BERT, Google will be able to analyze the entire phrase considering the context of a word from the terms that come before and after it (hence the “bidirectional” meaning of the name).

See also  How to give online courses? Content planning tips.

It is as if Google now understood the user’s intention when performing a search.

BERT in action

In the of the system, Google presented some examples of the impact of BERT on the SERP.

The first shows two results for the search “2019 Brazil traveler to US need a visa” (something like “2019 Brazil tourist in the US needs a visa”).

In this sentence, the word “to” indicates that the user wants to know if a Brazilian tourist needs a visa to travel to the US.

Before, Google simply did not understand this relationship and displayed results about US citizens traveling to Brazil, which is precisely the opposite of what the user wanted to investigate.

Another example of this technology in action would be the results for the search “can you get medicine for someone pharmacy”.

It is likely that the user in the example above wants to know if there is any problem in buying a prescription medicine without the patient being present, but it seems that the results are not aligned with this doubt.

Currently, the search engine chooses keywords such as “drug” and “pharmacy” completely ignoring the context. For this reason, the results may differ on how to get a prescription, for example.

However, since BERT considers the entire sequence of words, the results change completely. With it, for example, already the first entry informs whether or not it is possible to obtain prescription drugs from a person other than the patient.

In other words, Google is able to understand more precisely the intention of a search and thus can offer more precise results.

See also  Virtual learning environment: the 9 main characteristics

How is the RankBrain?

For those who don’t know, RankBrain was the first method based on developed by Google to better understand the searches made by users.

Analyzing the terms used in the searches, the content of the indexed websites and the behavior of the user in the clicks that occur on the response page, RankBrain aims to understand what the user meant with that search and what really want to find out.

In addition, this algorithm also adjusts the results according to the performance of each page in previous similar searches.

As you may have seen, the objective of RankBrain is very similar to that of BERT: to understand the search intention of users in order to offer more precise results.

However, the two technologies are not mutually exclusive. On the contrary, they complement each other.

In this way, BERT can work as a complementary method to analyze and understand content and searches.

Thus, depending on the situation, Google can use RankBrain, BERT or a combination of both to offer the best possible results to the user.

Impacts of BERT on other Google products

Google’s BERT announcement refers only to the company’s search tools, but other Google products are likely to be affected by the new technology as well.

One of them is Google Assistant. When any search carried out with the virtual assistant returns some in the search results, these can be affected by the BERT.

In addition, there is the expectation that platforms such as YouTube and Google Maps will also receive their influence, since both are widely used for searching for content on the Internet.

See also  Get to know the Assignment Rules |

How to optimize content for BERT?

And now the question that arises is: how to optimize your pages and content for BERT? Will this be possible?

The answer has been given by Danny Sullivan, Google spokesman on matters related to search.

There’s nothing to optimize for with BERT, nor anything for anyone to be rethinking. The fundamentals of us seeking to reward great content remain unchanged.

—Danny Sullivan (@dannysullivan)

Translation: “There is nothing to be optimized or rethought for BERT. Our quest to reward quality content continues unabated.”

Over the years, Google’s advice to achieve a good ranking in the SERP has been to create relevant, quality content that responds to user questions.

And since BERT was created to interpret the intent of each search, it stands to reason that providing quality content remains Google’s top recommendation.

Consequently, currently they can now concentrate more on writing in the best possible way instead of thinking about how they are going to write to please machines and algorithms.

And, well, now you know the main novelties of BERT, Google’s new artificial intelligence technology. Also take the opportunity to learn more about the and the main tasks you need to execute to conquer the SERP.

Loading Facebook Comments ...
Loading Disqus Comments ...