Ingredients Analysis Quality Evaluation - June 2022: Difference between revisions

From Open Food Facts wiki
VisualWikitext
No edit summary
 
(16 intermediate revisions by 4 users not shown)
Line 1: Line 1:
Evaluation of the quality of [[Ingredients Extraction and Analysis]] so that we can measure the improvements.
Evaluation of the quality of [[Ingredients Extraction and Analysis]] so that we can measure the improvements.
 
[[Category:Metrics]]
== Ingredients parsing and recognition ==
== Ingredients parsing and recognition ==


Line 21: Line 21:
{| class="wikitable"
{| class="wikitable"
|-
|-
!  !! 2022-06-23 ||
!  !! 2022-06-23 || 2022-06-27
|-
|-
| [https://in.openfoodfacts.org/ingredients?stats=1 All products:] ||
| [https://in.openfoodfacts.org/ingredients?stats=1&no_cache=1 All products:] ||
<pre>
<pre>
known 776 (23.07%) 8444 (69.62%)
known 776 (23.07%) 8444 (69.62%)
Line 31: Line 31:
  ||
  ||
<pre>
<pre>
 
known 780 (23.10%) 9062 (71.49%)
unknown 2596 (76.90%) 3614 (28.51%)
all 3376 (100.00%) 12676 (100.00%)
</pre>
</pre>
|-
|-
| [https://in.openfoodfacts.org/popularity/top-10000-in-scans-2021/ingredients?stats=1 Top 10k most scanned products:] ||  
| [https://in.openfoodfacts.org/popularity/top-10000-in-scans-2021/ingredients?stats=1&no_cache=1 Top 10k most scanned products:] ||  
<pre>
<pre>
known 407 (35.83%) 2149 (69.23%)
known 407 (35.83%) 2149 (69.23%)
Line 41: Line 43:
</pre>
</pre>
||
||
 
<pre>
known 407 (36.02%) 2284 (71.38%)
unknown 723 (63.98%) 916 (28.62%)
all 1130 (100.00%) 3200 (100.00%)
</pre>
|}
|}


Line 50: Line 56:
!  !! 2022-06-23 ||
!  !! 2022-06-23 ||
|-
|-
| [https://uk.openfoodfacts.org/ingredients?stats=1 All products:] ||
| [https://uk.openfoodfacts.org/ingredients?stats=1&no_cache=1 All products:] ||
<pre>
<pre>
known 2591 (6.22%) 406797 (88.32%)
known 2591 (6.22%) 406797 (88.32%)
Line 61: Line 67:
</pre>
</pre>
|-
|-
| [https://uk.openfoodfacts.org/popularity/top-10000-gb-scans-2021/ingredients?stats=1 Top 10k most scanned products:] ||  
| [https://uk.openfoodfacts.org/popularity/top-10000-gb-scans-2021/ingredients?stats=1&no_cache=1 Top 10k most scanned products:] ||  
<pre>
<pre>
known 1664 (21.69%) 77617 (91.14%)
known 1664 (21.69%) 77617 (91.14%)
Line 77: Line 83:
!  !! 2022-06-23 ||
!  !! 2022-06-23 ||
|-
|-
| [https://us.openfoodfacts.org/ingredients?stats=1 All products:] ||
| [https://us.openfoodfacts.org/ingredients?stats=1&no_cache=1 All products:] ||
<pre>
<pre>
known 3027 (1.77%) 8121359 (91.22%)
known 3027 (1.77%)         8121359 (91.22%)
unknown 167758 (98.23%) 781910 (8.78%)
unknown 167758 (98.23%)         781910 (8.78%)
all 170785 (100.00%) 8903269 (100.00%)
all 170785 (100.00%) 8903269 (100.00%)
</pre>
</pre>
Line 88: Line 94:
</pre>
</pre>
|-
|-
| [https://us.openfoodfacts.org/popularity/top-10000-us-scans-2021/ingredients?stats=1 Top 10k most scanned products:] ||  
| [https://us.openfoodfacts.org/popularity/top-10000-us-scans-2021/ingredients?stats=1&no_cache=1 Top 10k most scanned products:] ||  
<pre>
<pre>
known 1619 (18.24%) 97755 (88.84%)
known 1619 (18.24%) 97755 (88.84%)
unknown 7255 (81.76%) 12283 (11.16%)
unknown 7255 (81.76%) 12283 (11.16%)
all 8874 (100.00%) 110038 (100.00%)
all 8874 (100.00%) 110038 (100.00%)
</pre>
||
|}
=== FR - French ===
{| class="wikitable"
|-
!  !! 2022-07-13 ||
|-
| [https://fr.openfoodfacts.org/ingredients?stats=1&no_cache=1 All products:] ||
<pre>
known 4440 (1.05%) 5069577 (88.03%)
unknown 419374 (98.95%) 689143 (11.97%)
all 423814 (100.00%) 5758720 (100.00%)
</pre>
||
<pre>
</pre>
|-
| [https://fr.openfoodfacts.org/popularity/top-10000-fr-scans-2021/ingredients?stats=1&no_cache=1 Top 10k most scanned products:] ||
<pre>
known 2436 (21.84%) 210027 (94.37%)
unknown 8718 (78.16%) 12527 (5.63%)
all 11154 (100.00%) 222554 (100.00%)
</pre>
||
|}
=== HR - Croatia ===
{| class="wikitable"
|-
!  !! 2022-09-20 ||
|-
| [https://hr.openfoodfacts.org/ingredients?stats=1&no_cache=1 All products:] ||
<pre>
known 680 (8.64%) 8476 (46.93%)
unknown 7187 (91.36%) 9584 (53.07%)
all 7867 (100.00%) 18060 (100.00%)
</pre>
||
<pre>
</pre>
|-
| [https://hr.openfoodfacts.org/popularity/top-10000-hr-scans-2021/ingredients?stats=1&no_cache=1 Top 10k most scanned products:] ||
<pre>
known 369 (12.05%) 2394 (42.61%)
unknown 2693 (87.95%) 3224 (57.39%)
all 3062 (100.00%) 5618 (100.00%)
</pre>
||
|}
=== PL - Polish - PN ===
{| class="wikitable"
|-
!  !! 2022-07-08 ||
|-
| [https://pl.openfoodfacts.org/ingredients?stats=1&no_cache=1 All products:] ||
<pre>
known 1215 (11.38%) 68425 (78.48%)
unknown 9457 (88.62%) 18758 (21.52%)
all 10672 (100.00%) 87183 (100.00%)
</pre>
||
<pre>
</pre>
|-
| [https://pl.openfoodfacts.org/popularity/top-10000-pl-scans-2021/ingredients?stats=1&no_cache=1 Top 10k most scanned products:] ||
<pre>
known 742 (16.75%) 21685 (77.06%)
unknown 3689 (83.25%) 6455 (22.94%)
all 4431 (100.00%) 28140 (100.00%)
</pre>
</pre>
||
||
Line 110: Line 198:
!  !! 2022-06-23 !!
!  !! 2022-06-23 !!
|-
|-
| [https://in.openfoodfacts.org/ingredients-analysis All products:] ||
| [https://in.openfoodfacts.org/ingredients-analysis?no_cache=1 All products:] ||
<pre>
<pre>
Vegetarian status unknown 477
Vegetarian status unknown 477
Vegan status unknown 389
Vegan status unknown         389
Palm oil content unknown 370
Palm oil content unknown 370
Non-vegan 184
Non-vegan                 184
Palm oil free 160
Palm oil free                 160
Vegetarian 160
Vegetarian                 160
Vegan 80
Vegan                         80
Palm oil 74
Palm oil                 74
May contain palm oil 47
May contain palm oil         47
Non-vegetarian 20
Non-vegetarian                 20
Maybe vegan 8
Maybe vegan                 8
Maybe vegetarian 7
Maybe vegetarian         7
</pre>
</pre>
  ||
  ||


|-
|-
| [https://in.openfoodfacts.org/popularity/top-10000-in-scans-2021/ingredients-analysis Top 10k most scanned products:]
| [https://in.openfoodfacts.org/popularity/top-10000-in-scans-2021/ingredients-analysis?no_cache=1 Top 10k most scanned products:]
  ||  
  ||  
<pre>
<pre>
Line 154: Line 242:
!  !! 2022-06-23 !!
!  !! 2022-06-23 !!
|-
|-
| [https://uk.openfoodfacts.org/ingredients-analysis All products:] ||
| [https://uk.openfoodfacts.org/ingredients-analysis?no_cache=1 All products:] ||
<pre>
<pre>
Vegetarian status unknown 8623
Vegetarian status unknown 8631
Palm oil content unknown 8378
Palm oil content unknown 8379
Non-vegan 7693
Non-vegan 7699
Vegetarian 7293
Vegetarian 7295
Vegan status unknown 6188
Vegan status unknown 6193
Palm oil free 5725
Palm oil free 5730
Vegan 5021
Vegan 5023
Non-vegetarian 2754
Non-vegetarian 2756
Palm oil 2660
Palm oil 2663
May contain palm oil 1648
May contain palm oil 1651
Maybe vegetarian 911
Maybe vegetarian 912
Maybe vegan 559
Maybe vegan 559
</pre>
</pre>
  ||
  ||


|-
|-
| [https://uk.openfoodfacts.org/popularity/top-10000-gb-scans-2021/ingredients-analysis Top 10k most scanned products:]
| [https://uk.openfoodfacts.org/popularity/top-10000-gb-scans-2021/ingredients-analysis?no_cache=1 Top 10k most scanned products:]
  ||  
  ||  
<pre>
<pre>
Vegetarian 1741
Vegetarian 1742
Palm oil content unknown 1472
Palm oil content unknown 1474
Vegetarian status unknown 1412
Vegetarian status unknown 1413
Palm oil free 1407
Palm oil free 1406
Non-vegan 1359
Non-vegan 1359
Vegan 1138
Vegan 1139
Vegan status unknown 1120
Vegan status unknown 1121
Palm oil 511
Palm oil 511
Non-vegetarian 434
Non-vegetarian 434
Line 198: Line 286:
!  !! 2022-06-23 !!
!  !! 2022-06-23 !!
|-
|-
| [https://us.openfoodfacts.org/ingredients-analysis All products:] ||
| [https://us.openfoodfacts.org/ingredients-analysis?no_cache=1 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>
  ||
  ||


|-
|-
| [https://us.openfoodfacts.org/popularity/top-10000-us-scans-2021/ingredients-analysis Top 10k most scanned products:]
| [https://us.openfoodfacts.org/popularity/top-10000-us-scans-2021/ingredients-analysis?no_cache=1 Top 10k most scanned products:]
  ||  
  ||  
<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>
||
 
|}
 
=== HR - Croatia ===
 
{| class="wikitable"
|-
!  !! 2022-09-20 !!
|-
| [https://hr.openfoodfacts.org/ingredients-analysis?no_cache=1 All products:] ||
<pre>
en:Vegetarian status unknown 706
en:Palm oil content unknown 656
en:Vegan status unknown 556
en:Non-vegan 206
en:Vegetarian 189
en:Vegan 165
en:Palm oil free 152
en:May contain palm oil 50
en:Palm oil 50
en:Non-vegetarian 29
en:Maybe vegetarian 8
en:Maybe vegan 5
</pre>
||
 
|-
| [https://hr.openfoodfacts.org/popularity/top-10000-hr-scans-2021/ingredients-analysis?no_cache=1 Top 10k most scanned products:]
||
<pre>
en:Vegetarian status unknown 267
en:Palm oil content unknown 248
en:Vegan status unknown 215
en:Non-vegan 65
en:Vegetarian 50
en:Palm oil free 45
en:Vegan 43
en:May contain palm oil 18
en:Palm oil 13
en:Non-vegetarian 6
en:Maybe vegetarian 2
en:Maybe vegan 2
</pre>
</pre>
||
||
Line 236: Line 368:
|}
|}


=== PL - Polish - PL ===
{| class="wikitable"
|-
!  !! 2022-07-08 !!
|-
| [https://pl.openfoodfacts.org/ingredients-analysis?no_cache=1 All products:] ||
<pre>
en:Vegetarian status unknown 3442
en:Palm oil content unknown 2571
en:Vegan status unknown 2297
en:Non-vegan 1756
Bez oleju palmowego 1336
en:Vegetarian 699
en:Vegan 581
en:May contain palm oil 435
en:Non-vegetarian 413
Olej palmowy 311
en:Maybe vegetarian 137
en:Maybe vegan 51
</pre>
||
|-
| [https://pl.openfoodfacts.org/popularity/top-10000-pl-scans-2021/ingredients-analysis?no_cache=1 Top 10k most scanned products:]
||
<pre>
en:Vegetarian status unknown 1382
en:Palm oil content unknown 1032
en:Vegan status unknown 964
en:Non-vegan 599
Bez oleju palmowego 491
en:Vegetarian 244
en:Vegan 187
en:May contain palm oil 142
en:Non-vegetarian 109
Olej palmowy 92
en:Maybe vegetarian 32
en:Maybe vegan 16
</pre>
||


|}


=== Observations ===
=== Observations ===
Line 242: Line 416:


[[Category:Project:Personalized_Search]]
[[Category:Project:Personalized_Search]]
[[Category:Data quality]]
[[Category:Ingredients]]

Latest revision as of 10:44, 7 August 2024

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 2022-06-27
All products: 
known	776 (23.07%)	8444 (69.62%)
unknown	2588 (76.93%)	3685 (30.38%)
all	3364 (100.00%)	12129 (100.00%)

known	780 (23.10%)	9062 (71.49%)
unknown	2596 (76.90%)	3614 (28.51%)
all	3376 (100.00%)	12676 (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%)

known	407 (36.02%)	2284 (71.38%)
unknown	723 (63.98%)	916 (28.62%)
all	1130 (100.00%)	3200 (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%)


FR - French

2022-07-13
All products: 
known	4440 (1.05%)	5069577 (88.03%)
unknown	419374 (98.95%)	689143 (11.97%)
all	423814 (100.00%)	5758720 (100.00%)
Top 10k most scanned products: 
known	2436 (21.84%)	210027 (94.37%)
unknown	8718 (78.16%)	12527 (5.63%)
all	11154 (100.00%)	222554 (100.00%)

HR - Croatia

2022-09-20
All products: 
known	680 (8.64%)	8476 (46.93%)
unknown	7187 (91.36%)	9584 (53.07%)
all	7867 (100.00%)	18060 (100.00%)
Top 10k most scanned products: 
known	369 (12.05%)	2394 (42.61%)
unknown	2693 (87.95%)	3224 (57.39%)
all	3062 (100.00%)	5618 (100.00%)

PL - Polish - PN

2022-07-08
All products: 
known	1215 (11.38%)	68425 (78.48%)
unknown	9457 (88.62%)	18758 (21.52%)
all	10672 (100.00%)	87183 (100.00%)
Top 10k most scanned products: 
known	742 (16.75%)	21685 (77.06%)
unknown	3689 (83.25%)	6455 (22.94%)
all	4431 (100.00%)	28140 (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

HR - Croatia

2022-09-20
All products: 
en:Vegetarian status unknown	706	
en:Palm oil content unknown	656	
en:Vegan status unknown	556	
en:Non-vegan	206	
en:Vegetarian	189	
en:Vegan	165	
en:Palm oil free	152	
en:May contain palm oil	50	
en:Palm oil	50	
en:Non-vegetarian	29	
en:Maybe vegetarian	8	
en:Maybe vegan	5
Top 10k most scanned products: 
en:Vegetarian status unknown	267	
en:Palm oil content unknown	248	
en:Vegan status unknown	215	
en:Non-vegan	65	
en:Vegetarian	50	
en:Palm oil free	45	
en:Vegan	43	
en:May contain palm oil	18	
en:Palm oil	13	
en:Non-vegetarian	6	
en:Maybe vegetarian	2	
en:Maybe vegan	2

PL - Polish - PL

2022-07-08
All products: 
en:Vegetarian status unknown	3442	
en:Palm oil content unknown	2571	
en:Vegan status unknown	2297	
en:Non-vegan	1756	
Bez oleju palmowego	1336	
en:Vegetarian	699	
en:Vegan	581	
en:May contain palm oil	435	
en:Non-vegetarian	413	
Olej palmowy	311	
en:Maybe vegetarian	137	
en:Maybe vegan	51
Top 10k most scanned products: 
en:Vegetarian status unknown	1382	
en:Palm oil content unknown	1032	
en:Vegan status unknown	964	
en:Non-vegan	599	
Bez oleju palmowego	491	
en:Vegetarian	244	
en:Vegan	187	
en:May contain palm oil	142	
en:Non-vegetarian	109	
Olej palmowy	92	
en:Maybe vegetarian	32	
en:Maybe vegan	16

Observations

Retrieved from "https://test-wiki.openfoodfacts.org/index.php?title=Ingredients_Analysis_Quality_Evaluation_-_June_2022&oldid=21998"