Case Study:
Google’s understanding of the Property (Real Estate) sector

July 2020

Executive Summary

The UK Government has waived stamp duty (the tax on purchasing a home), for any purchase up to £500,000 for the next 9 months in an effort to keep liquidity in the market post-lockdown. We looked at how well Google's natural language algorithms work in this competitive environment.

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 Real Estate sector.

InLinks analyzed the page content of the top 10 Google results (in the UK Market) ranking for the phrase stamp duty 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 Real Estate sector

The results showed that 25.1% of entities seen on the results in the Real Estate sector SERPS (search engine Results pages) were positively identified by Google.

This compares to 21.3% 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.

 

Real Estate Industry Google Analysis InLinks Analysis
Avg. Number of words per page 1755
Avg. Number of Topics per page 9.9 39.4
Benchmark - Avg. nb of entities/page (all sectors) 9.4 45.7
Of which, Topic types are:    
- Persons 6 4
- Organizations 19 26
- Cities & geo. areas 4 4
- Concepts 18 168
Semantic Density   4.9

How the research was conducted

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

#bbc, #gov.uk, #moneyadviceservice.org.uk, #moneysavingexpert, #stampdutycalculator.org.uk, #telegraph, #thesun, #which

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:

  • 18 concepts, including England (detected 9 times) Stamp duty in the United Kingdom (7) Wales (7)
  • 19 organizations, including HM Revenue and Customs (5) WhatsApp (2) LinkedIn (2)
  • 3 geographical areas, including Northern Ireland (European Parliament constituency) (8) United Kingdom (6) West Country (1)
  • 6 persons, including Rishi Sunak (3) Boris Johnson (1) Philip Hammond (1)
  • 1 city, including London (2)

Errors in Google’s Detection Rate

Here are some errors in the categorization of entities:

  • England categorized as a concept instead of geographical area
  • Wales categorized as a concept instead of geographical area
  • Scotland categorized as a concept instead of geographical area

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

  • Tax (seen 10 times) => NOT detected by Google
  • United Kingdom (8) => detected by Google
  • House (8) => NOT detected by Google
  • Purchasing (8) => NOT detected by Google
  • Real property (8) => NOT detected by Google
  • Stamp duty (8) => detected by Google
  • Real estate (8) => NOT detected by Google
  • Property (7) => NOT detected by Google
  • England (7) => detected by Google
  • Mortgage loan (7) => NOT detected by Google
  • Money (6) => detected by Google
  • Price (6) => NOT detected by Google
  • Rate (mathematics) (6) => NOT detected by Google
  • Calendar date (5) => NOT detected by Google
  • Scotland (5) => detected by Google

How can the Real Estate 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 Schema.org/WebPage and the "about" and mentions" properties for important concepts such as House, Real property, Real estate.

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 Real Estate market, based on its NLP algorithms remains limited at 25.1% for this industry. Businesses either need to improve their schema or make their content more understandable by Google to improve its level of understanding.

 

© 2019-2020 - InLinks.net - About us - Terms of Use - Privacy Policy