Case Study:
Google’s understanding of the Law sector

June 2020

Executive Summary

Google is known to be extra careful when returning results for "Your Money or Your Life" terms. It is therefore encouraging that Google's understanding of the topics involved in the black lives matter movement is the strongest we have looked at to dat. Even so, whilst there is a debate to be had around whether this topic should be categorized in society rather than law, our systems categorixed this as a law issue, because the concepts of "justice" and "racism" were prevalent within the content returned. "Justice" and "racism", however, are concepts that Google did not seem to pick up. It was also interesting to note that Google returned severla social media and news sites, demonstrating that it feels the query deserves freshness of results. These were interspersed with four different results from, suggesting that Google has made a strong connection between the site and the topic.


Google uses Natural Language Processing (NLP) routines to convert its understanding of text into topics and concepts (Entities). We looked out how much understanding Google misses using this approach in the Law sector.

InLinks analyzed the page content of the top 10 Google results (in the US Market) ranking for the phrase black lives matter and compared the Named Entities recognized by Google’s NLP API with the proprietory routines designed by Inlinks to uncover gaps in Google’s machine learning in the Law sector

The results showed that 36.4% of entities seen on the results in the Law sector SERPS (search engine Results pages) were positively identified by Google.

This compares to 20.7% average across all analyzed industry sectors.

How the Sector Compares

Different sectors tend to be analyzed with a different degree of accuracy by the search engines. This stems from two main challenges.

  1. the more demand there is by consumers within a given sector, the more the need for search engines to apply more sophisticated entity recognition to better answer user queries.
  2. the more sophisticated the industry is in creating search-friendly content, the more search engines can surface topics and concepts.


Law Industry Google Analysis InLinks Analysis
Avg. Number of words per page 1565
Avg. Number of Topics per page 13.1 36
Benchmark - Avg. nb of entities/page (all sectors) 9.4 46.9
Of which, Topic types are:    
- Persons 25 5
- Organizations 21 22
- Cities & geo. areas 21 16
- Concepts 20 171
Semantic Density   4.5

How the research was conducted

Google’s Search API returned URLs for the following sites competing for this phrase:

#blacklivesmatter, #en.wikipedia, #m4bl, #twitter, #facebook, #instagram, #theguardian

The texts of each page are then sent to Google’s NLP API, in order to determine which entities are identified by the search engine. These are important for search since Google is then able to link these to its Knowledge Graph to feed its services including Google Discover, Google search, Voice Search and Google News. (Although, correct identification does not guarantee inclusion in these results)

Here is first of all the synthesis of the results returned by Google:

  • 25 persons, including Trayvon Martin (detected 4 times) Patrisse Cullors (3) Alicia Garza (3)
  • 20 concepts, including Black Lives Matter (8) ZIP Code (3) Killing of George Floyd (2)
  • 15 geographical areas, including United States (7) United Kingdom (3) Canada (3)
  • 21 organizations, including Spanish language (2) Opal Tometi (2) Movement for Black Lives (2)
  • 6 cities, including Minneapolis (5) South Bend, Indiana (1) Ferguson, Missouri (1)
  • 2 events, including Shooting of Michael Brown (3) Labor Day (1)

Errors in Google’s Detection Rate

Here are some errors in the categorization of entities:

  • Minnesota categorized as a concept instead of geographical area
  • Missouri categorized as a concept instead of geographical area

Most important entities (provided by InLinks), compared to those identified by Google:

  • Black Lives Matter (seen 8 times) => detected by Google
  • Justice (7) => NOT detected by Google
  • United States (6) => detected by Google
  • racism (5) => NOT detected by Google
  • Minneapolis (5) => detected by Google
  • United Kingdom (5) => detected by Google
  • Activism (5) => NOT detected by Google
  • Acquittal (4) => NOT detected by Google
  • Killing of George Floyd (4) => detected by Google
  • Black (4) => NOT detected by Google
  • Canada (4) => detected by Google
  • Violence (4) => NOT detected by Google
  • Shooting of Trayvon Martin (4) => NOT detected by Google
  • Family (4) => NOT detected by Google
  • Community (4) => NOT detected by Google

How can the Law Industry benefit from this report?

By understanding where Google is failing to recognize important concepts within the industry, there is an opportunity for companies in the sector to write clearer content that Google can better understand.

Another option is to explicitly state these concepts in Webpage schema for machine learning algorithms to take into account. This would require using and the "about" and mentions" properties for important concepts such as .


Internal linking of topics topages dedicated to each important topic will also help to reduce cannibalisation of content in Google’s understanding of contect within your content.

In Summary

Google's understanding of the Law market, based on its NLP algorithms remains limited at 36.4% for this industry. Businesses either need to improve their schema or make their content more understandable by Google to improve its level of understanding.

SERP results

Bureau of Land Management, Black Lives Matter, Killing of George Floyd, Pete Buttigieg, United States, Emergency medical technician, Minneapolis, ZIP Code, South Bend, Indiana, Social media

Black Lives Matter, United States, George Zimmerman, Patrisse Cullors, Trayvon Martin, African Americans, Ferguson, Missouri, Alicia Garza, Movement for Black Lives, Anti-Apartheid Movement, Opal Tometi, Blue Lives Matter, All Lives Matter, Facebook, Shooting of Michael Brown, New York City, George Floyd, Death of Eric Garner, St. Louis County, Missouri, Democratic Party (United States), Minnesota, Minneapolis, Occupy Wall Street, United Kingdom, Australia, Germany, New Zealand, Republican Party (United States), Rudy Giuliani, Black Power, Al Sharpton, Pan-Africanism, Missouri, Palestinians, Israel, National Action Network, Jesse Jackson, Rainbow/PUSH, Manhattan, Union Square, Manhattan

Black Lives Matter, Trayvon Martin, Canada, United Kingdom, United States, ZIP Code

Black Lives Matter, Killing of George Floyd, Nonprofit organization, Alicia Garza, Opal Tometi, Patrisse Cullors, United States, English language, French language, Canada, Spanish language, Brazil, Portuguese language, German language, Minneapolis, YouTube

Black Lives Matter, Trayvon Martin, Dream Defenders, Florida State Capitol, George Zimmerman, Black people, Shooting of Michael Brown

Movement for Black Lives, United States, Black people, White nationalism

African Americans, Black Lives Matter, George Zimmerman, Ferguson unrest, Opal Tometi, Alicia Garza, Patrisse Cullors, Trayvon Martin, St. Louis, Labor Day, Shooting of Michael Brown, Darnell L. Moore, Death of Sandra Bland, Shooting of Walter Scott, Shooting of Tamir Rice, ZIP Code

Black Lives Matter, Twitter, Minneapolis, United States

Login, Instagram, Amplifier, Spanish language, Spain, Portugal, Norwegian language, Malay language, Swedish language, Russian language, Canada

Edward Colston, United Kingdom, Black Lives Matter, United States, Australia, Minneapolis, George Floyd, Keir Starmer, Dan Tehan, Long Bay Correctional Centre, Thomas Chatterton Williams, IndigenousX, The Guardian, Raheem Sterling, London, Manchester City F.C., Newsnight

© 2019-2020 - - About us - Terms of Use - Privacy Policy