Difference between revisions of "Ingredients Analysis Quality Evaluation - June 2022"

From Open Food Facts wiki
Jump to navigation Jump to search
Line 200: Line 200:
 
| [https://us.openfoodfacts.org/ingredients-analysis All products:] ||
 
| [https://us.openfoodfacts.org/ingredients-analysis All products:] ||
 
<pre>
 
<pre>
Vegetarian status unknown 212861
+
Vegetarian status unknown 212874
Palm oil content unknown 176245
+
Palm oil content unknown 176193
 
Non-vegan 146466
 
Non-vegan 146466
Vegan status unknown 126220
+
Vegan status unknown 126232
Palm oil free 85478
+
Palm oil free 85546
Vegetarian 51116
+
Vegetarian 51118
Non-vegetarian 45193
+
Non-vegetarian 45192
Vegan 44942
+
Vegan 44944
Palm oil 37921
+
Palm oil 37920
 
May contain palm oil 30916
 
May contain palm oil 30916
Maybe vegetarian 21742
+
Maybe vegetarian 21744
Maybe vegan 13279
+
Maybe vegan 13281
 
</pre>
 
</pre>
 
  ||
 
  ||
Line 220: Line 220:
 
<pre>
 
<pre>
 
Vegetarian status unknown 2914
 
Vegetarian status unknown 2914
Palm oil content unknown 2488
+
Palm oil content unknown 2486
 
Vegan status unknown 1954
 
Vegan status unknown 1954
 
Non-vegan 1552
 
Non-vegan 1552
Palm oil free 1223
+
Palm oil free 1226
 
Vegetarian 944
 
Vegetarian 944
 
Vegan 847
 
Vegan 847
 
Palm oil 405
 
Palm oil 405
 
Non-vegetarian 391
 
Non-vegetarian 391
May contain palm oil 361
+
May contain palm oil 360
 
Maybe vegetarian 248
 
Maybe vegetarian 248
Maybe vegan 143
+
Maybe vegan 143
 
</pre>
 
</pre>
 
||
 
||
  
 
|}
 
|}
 
 
  
 
=== Observations ===
 
=== Observations ===

Revision as of 16:17, 24 June 2022

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.


EN - English - India

2022-06-23
All products:
known	776 (23.07%)	8444 (69.62%)
unknown	2588 (76.93%)	3685 (30.38%)
all	3364 (100.00%)	12129 (100.00%)

Top 10k most scanned products:
known	407 (35.83%)	2149 (69.23%)
unknown	729 (64.17%)	955 (30.77%)
all	1136 (100.00%)	3104 (100.00%)

EN - English - UK

2022-06-23
All products:
known	2591 (6.22%)	406797 (88.32%)
unknown	39034 (93.78%)	53807 (11.68%)
all	41625 (100.00%)	460604 (100.00%)

Top 10k most scanned products:
known	1664 (21.69%)	77617 (91.14%)
unknown	6008 (78.31%)	7546 (8.86%)
all	7672 (100.00%)	85163 (100.00%)

EN - English - US

2022-06-23
All products:
known	3027 (1.77%)	8121359 (91.22%)
unknown	167758 (98.23%)	781910 (8.78%)
all	170785 (100.00%)	8903269 (100.00%)

Top 10k most scanned products:
known	1619 (18.24%)	97755 (88.84%)
unknown	7255 (81.76%)	12283 (11.16%)
all	8874 (100.00%)	110038 (100.00%)

Ingredients analysis

For each product, once we have parsed the ingredients list to separate each ingredient and match them to our taxonomy, we can analyze if the products are vegan, vegetarian, without palm oil etc.

To mark a product as non-vegan etc. we only need to find one non-vegan ingredient. But to mark a product as vegan, we need to be sure that we have been able to correctly recognize all ingredients so that we can verify that all of them are vegan.

EN - English - IN

2022-06-23
All products:
Vegetarian status unknown	477	
Vegan status unknown	389	
Palm oil content unknown	370	
Non-vegan	184	
Palm oil free	160	
Vegetarian	160	
Vegan	80	
Palm oil	74	
May contain palm oil	47	
Non-vegetarian	20	
Maybe vegan	8	
Maybe vegetarian	7		
Top 10k most scanned products:
Vegetarian status unknown	127	
Vegan status unknown	100	
Palm oil content unknown	93	
Non-vegan	43	
Palm oil free	37	
Vegetarian	27	
Palm oil	22	
Vegan	13	
May contain palm oil	5	
Non-vegetarian	3	
Maybe vegan	2	
Maybe vegetarian	2			

EN - English - UK

2022-06-23
All products:
Vegetarian status unknown	8631	
Palm oil content unknown	8379	
Non-vegan	7699	
Vegetarian	7295	
Vegan status unknown	6193	
Palm oil free	5730	
Vegan	5023	
Non-vegetarian	2756	
Palm oil	2663	
May contain palm oil	1651	
Maybe vegetarian	912	
Maybe vegan	559		
Top 10k most scanned products:
Vegetarian	1742	
Palm oil content unknown	1474	
Vegetarian status unknown	1413	
Palm oil free	1406	
Non-vegan	1359	
Vegan	1139	
Vegan status unknown	1121	
Palm oil	511	
Non-vegetarian	434	
May contain palm oil	270	
Maybe vegetarian	159	
Maybe vegan	112	

EN - English - US

2022-06-23
All products:
Vegetarian status unknown	212874	
Palm oil content unknown	176193	
Non-vegan	146466	
Vegan status unknown	126232	
Palm oil free	85546	
Vegetarian	51118	
Non-vegetarian	45192	
Vegan	44944	
Palm oil	37920	
May contain palm oil	30916	
Maybe vegetarian	21744	
Maybe vegan	13281	
Top 10k most scanned products:
Vegetarian status unknown	2914	
Palm oil content unknown	2486	
Vegan status unknown	1954	
Non-vegan	1552	
Palm oil free	1226	
Vegetarian	944	
Vegan	847	
Palm oil	405	
Non-vegetarian	391	
May contain palm oil	360	
Maybe vegetarian	248	
Maybe vegan	143	

Observations