Difference between revisions of "Ingredients Analysis Quality Evaluation - January 2025"

From Open Food Facts wiki
Jump to navigation Jump to search
Line 19: Line 19:
 
=== FR - French ===
 
=== FR - French ===
 
=== JP - Japanese ===
 
=== JP - Japanese ===
 +
 +
 +
4487 原材料:
 +
{| class="wikitable"
 +
!Type
 +
!Unique tags
 +
!Occurrences
 +
|-
 +
|known
 +
|1026 (22.87%)
 +
|18832 (80.41%)
 +
|-
 +
|unknown
 +
|3461 (77.13%)
 +
|4587 (19.59%)
 +
|-
 +
|all
 +
|4487 (100.00%)
 +
|23419 (100.00%)
 +
|}
  
 
=== HR - Croatian ===
 
=== HR - Croatian ===
 +
 +
 +
6468 sastojci:
 +
{| class="wikitable"
 +
!Type
 +
!Unique tags
 +
!Occurrences
 +
|-
 +
|known
 +
|1751 (27.07%)
 +
|44073 (89.55%)
 +
|-
 +
|unknown
 +
|4717 (72.93%)
 +
|5141 (10.45%)
 +
|-
 +
|all
 +
|6468 (100.00%)
 +
|49214 (100.00%)
 +
|}
  
 
=== PL - Polish ===
 
=== PL - Polish ===
 +
 +
8971 składniki:
 +
{| class="wikitable"
 +
!Type
 +
!Unique tags
 +
!Occurrences
 +
|-
 +
|known
 +
|2135 (23.80%)
 +
|184483 (95.40%)
 +
|-
 +
|unknown
 +
|6836 (76.20%)
 +
|8899 (4.60%)
 +
|-
 +
|all
 +
|8971 (100.00%)
 +
|193382 (100.00%)
 +
|}
  
  

Revision as of 16:08, 17 January 2025

Evaluation of the quality of Ingredients Extraction and Analysis so that we can measure the improvements.

Ingredients parsing and recognition

For each product, the ingredients list is parsed to separate each ingredient. Ingredients that we can match to our multilingual ingredients taxonomy as marked as "known", others as "unknown".

There are different reasons an ingredient can be marked as unknown:

  • The input ingredient list is incorrect (misspellings etc.)
  • The ingredients list contains other things than ingredients, and we have not been able to split it at the right place.
  • We have not been able to parse a particular sentence structure or formatting (e.g., "a drop of delicious honey with a shower of powder sugar")
  • The ingredient is not yet present in our taxonomy (or not with the right synonym or in the right language)

In the table below,

  • the first column of numbers corresponds to the number of unique ingredients across all products.
  • And the second column of number corresponds to the number of occurrences of those ingredients. e.g., if a specific ingredient appears in 5 products, it is counted 5 times.


FR - French

JP - Japanese

4487 原材料:

Type Unique tags Occurrences
known 1026 (22.87%) 18832 (80.41%)
unknown 3461 (77.13%) 4587 (19.59%)
all 4487 (100.00%) 23419 (100.00%)

HR - Croatian

6468 sastojci:

Type Unique tags Occurrences
known 1751 (27.07%) 44073 (89.55%)
unknown 4717 (72.93%) 5141 (10.45%)
all 6468 (100.00%) 49214 (100.00%)

PL - Polish

8971 składniki:

Type Unique tags Occurrences
known 2135 (23.80%) 184483 (95.40%)
unknown 6836 (76.20%) 8899 (4.60%)
all 8971 (100.00%) 193382 (100.00%)


UK + English

Observations