Case Study:
Google’s understanding of the Clothing sector
July 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 Clothing sector.
InLinks analyzed the page content of the top 10 Google results (in the CA Market) ranking for the phrase responsible fashion 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 Clothing sector
The results showed that 16% of entities seen on the results in the Clothing sector SERPS (search engine Results pages) were positively identified by Google.
This compares to 21.1% 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.
| Clothing Industry | Google Analysis | InLinks Analysis |
|---|---|---|
| Avg. Number of words per page | 1288 | |
| Avg. Number of Topics per page | 12.3 | 76.4 |
| Benchmark - Avg. nb of entities/page (all sectors) | 9.3 | 46.1 |
| Of which, Topic types are: | ||
| - Persons | 6 | 3 |
| - Organizations | 31 | 28 |
| - Cities & geo. areas | 27 | 23 |
| - Concepts | 18 | 364 |
| Semantic Density | 9.5 | |
How the research was conducted
Google’s Search API returned URLs for the following sites competing for this phrase:
#vancourier, #georgebrown.ocls.ca, #themontrealfashionsociety, #alternativesjournal.ca, #lordsshoes.ca, #pinterest.ca, #thestar
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:
- 31 organizations, including Università Cattolica del Sacro Cuore (detected 2 times) Polytechnic University of Milan (2) SDA Bocconi School of Management (2)
- 18 geographical areas, including 2013 Dhaka garment factory collapse (3) Bangladesh (3) Solomeo (2)
- 18 concepts, including Fashion (2) English language (1) Clothing industry (1)
- 9 cities, including Milan (2) Hong Kong (1) Shanghai (1)
- 6 persons, including Frances of Rome (1) Mahatma Gandhi (1) George Brown College (1)
- 1 event, including United Nations Framework Convention on Climate Change (1)
- 1 person, including Theresa May (1)
Errors in Google’s Detection Rate
No errors were found.
Most important entities (provided by InLinks), compared to those identified by Google:
- Fashion (seen 8 times) => detected by Google
- Sustainability (6) => NOT detected by Google
- Clothing (6) => NOT detected by Google
- Industry (6) => NOT detected by Google
- Product (business) (6) => NOT detected by Google
- Natural environment (5) => NOT detected by Google
- Textile (5) => NOT detected by Google
- Best practice (5) => NOT detected by Google
- Franchising (4) => NOT detected by Google
- Consumer (4) => NOT detected by Google
- Retail (4) => NOT detected by Google
- Workforce (4) => NOT detected by Google
- Transparency (market) (4) => NOT detected by Google
- Ethics (4) => NOT detected by Google
- Manufacturing (4) => NOT detected by Google
How can the Clothing 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 Clothing, Transparency (market).
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 Clothing market, based on its NLP algorithms remains limited at 16% for this industry. Businesses either need to improve their schema or make their content more understandable by Google to improve its level of understanding.