Case Study:
Google’s understanding of the Education sector
November 2020
Executive Summary
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 Education sector.
InLinks analyzed the page content of the top 10 Google results (in the UK Market) ranking for the phrase financial technology 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 Education sector
The results showed that 12% of entities seen on the results in the Education sector SERPS (search engine results pages) were positively identified by Google.
This compares to 18.9% 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.
- 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.
- the more sophisticated the industry is in creating search-friendly content, the more search engines can surface topics and concepts.
| Education Industry | Google Analysis | InLinks Analysis |
|---|---|---|
| Avg. Number of words per page | 7205 | |
| Avg. Number of Topics per page | 8.9 | 74.4 |
| Benchmark - Avg. nb of entities/page (all sectors) | 8.8 | 47.6 |
| Of which, Topic types are: | ||
| - Persons | 2 | 0 |
| - Organizations | 22 | 29 |
| - Cities & geo. areas | 11 | 13 |
| - Concepts | 27 | 337 |
| Semantic Density | 9.3 | |
How the research was conducted
Google’s Search API returned URLs for the following sites competing for this phrase:
#courses.uwe.ac.uk, #bangor.ac.uk, #birmingham.ac.uk, #bristol.ac.uk, #essex.ac.uk, #glos.ac.uk, #imperial.ac.uk, #pwc, #shu.ac.uk
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:
- 27 concepts, including Financial technology (detected 4 times) Coronavirus (3) Summer school (2)
- 22 organizations, including National Health Service (2) University (2) Imperial College Business School (2)
- 5 geographical areas, including United Kingdom (6) Sheffield Hallam University (1) Canary Wharf (1)
- 6 cities, including London (4) Sheffield (1) Bristol (1)
- 2 persons, including Mastère spécialisé (2) Alumnus (1)
Errors in Google’s Detection Rate
Here are some errors in the categorization of entities:
- Essex categorized as a concept instead of a geographical area
Most important entities (provided by InLinks), compared to those identified by Google:
- Graduate school (seen 8 times) => NOT detected by Google
- Research (8) => NOT detected by Google
- Business (8) => NOT detected by Google
- Financial technology (8) => detected by Google
- Employment (7) => NOT detected by Google
- Innovation (7) => NOT detected by Google
- Service (economics) (7) => NOT detected by Google
- Course (education) (7) => NOT detected by Google
- Student (7) => NOT detected by Google
- Management (7) => NOT detected by Google
- Industry classification (6) => NOT detected by Google
- Information technology (6) => NOT detected by Google
- Learning (6) => NOT detected by Google
- Knowledge base (6) => NOT detected by Google
- Higher education (6) => NOT detected by Google
How can the Education 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 Graduate school, Course (education), Student, Learning, Higher education.
Internal linking of topics to pages 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 Education market, based on its NLP algorithms remains limited at 12% 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 used in this analysis and the topics Google returned:
https://www.shu.ac.uk/courses/accounting-banking-and-finance/bsc-honours-financial-technology/full-time
Sheffield Hallam University, Bachelor of Science, Sheffield, Master of Business Administration, United Kingdom, English language
https://www.pwc.com/gx/en/industries/financial-services/publications/financial-services-technology-2020-and-beyond-embracing-disruption.html
Financial technology, Blockchain.com
https://www.bristol.ac.uk/study/postgraduate/2021/eng/msc-financial-technology-with-data-science/
Master of Science, University of Bristol, Bristol, Alipay, United Kingdom, Computational statistics, Software development, Artificial intelligence, Alumnus, English language, European Union, London
https://www.bangor.ac.uk/business/undergraduate-modules/ASB-3008
Bangor, Maine, University, Postgraduate research
https://www.glos.ac.uk/courses/postgraduate/fnt/pages/financial-technology-msc-msc.aspx
Financial technology, Master of Science, East London, London School of Economics, Canary Wharf, Bank of England, Regulatory technology, Problem-based learning, University of Gloucestershire, European Union, St. James's Place plc, United Kingdom
https://www.imperial.ac.uk/business-school/programmes/msc-financial-technology/programme/
London, Imperial College Business School, United Kingdom, Master of Finance, Mastère spécialisé, Master of Science in Business Analytics, Research institute, Summer school, Imperial College London, Coronavirus, Environmental health, Dean's List, National Health Service
https://www.birmingham.ac.uk/postgraduate/courses/taught/business/fintech.aspx
University, Python (programming language), Bloomberg L.P., Coronavirus disease 2019, Data stream, Birmingham, Big data, EFMD Quality Improvement System, Compustat, Association to Advance Collegiate Schools of Business, United Kingdom, BoardEx, Capital IQ, Center for Research in Security Prices, Coronavirus
https://courses.uwe.ac.uk/N3I212/financial-technology-fintech
Financial technology, University of the West of England, Bristol
https://www.imperial.ac.uk/business-school/programmes/msc-financial-technology/admissions/entry-requirements/
Imperial College Business School, Master of Finance, London, Mastère spécialisé, Master of Science in Business Analytics, Research institute, Summer school, Imperial College London, Coronavirus, Environmental health, Dean's List, National Health Service
https://www.essex.ac.uk/courses/pg01381/1/msc-financial-technology-economics
Economics, Financial technology, UCAS, Essex, London, Europe, HM Treasury, Schroders, Mathematics, Microeconomics, United Kingdom, Macroeconomics