Google BERT is a new search algorithm. How will the ranking change and what to do now?

Google is not tired of pleasing its users and officially introduced a new search algorithm - Google BERT.



What is known about this and what is the point? Let's get it right.



Google BERT is a search engine algorithm designed to improve the relevance of search results due to the ability to analyze not key phrases, but sentences.

The abbreviation BERT means the following - Bidirectional Encoder Representations from Transformers, which, translated into Russian, means: bidirectional neural network encoder. To obtain a better result, a neural network is used, which is able to give the search engine understanding, including in different languages. At the moment, the algorithm is used for 10% of queries to the search engine, mainly the United States. The main language for testing is English and in the future it is planned to use most languages ​​and countries for SERP.



The main difference between BERT is the ability to analyze the query as a whole sentence (including prepositions, phrases) and select the relevant result, focusing on the context.

At the moment, the best recommendation for optimizing the site for Google BERT is to adapt texts for people and expand the semantic core of the page, thereby attracting more traffic to pages on which the information has a structure, intuitive access to the content and its placement taking into account the information architecture.



In terms of improving the intent, it is advisable to expand the pages with text and analyze search queries for which traffic was attracted with the inclusion of additional relevant key phrases from the search visibility. Search visibility is uploaded through special services. You can also add relevant phrases from Google, Bing and Yandex search suggestions to the content and analyze the internal search logs. A nice bonus is the appearance in this source of low-frequency phrases that are not in other systems.



conclusions



Google considers the introduction of the BERT ranking algorithm the largest breakthrough in the last 5 years and one of the most significant achievements in the history of search services (included in the Google Al First strategy). For more information on starting to use the BERT ranking algorithm, see the official Google blog. The challenge that BERT faces is solving natural language processing or natural language processing problems.

The key points influenced by the algorithm are:





For a smoother transition to the algorithm, you should expand the list of key phrases with similar ones. How to prepare for the arrival of the algorithm? It makes sense to expand the list of key phrases with similar ones.



For Google users, BERT will be a valuable update since getting relevant results in search results will become easier, which also affects the use of voice search.



image







All Articles