Changes

Jump to navigation Jump to search
no edit summary
Line 1: Line 1:  
This page describes the concrete actions that can be taken to improve ingredients analysis in a specific language.
 
This page describes the concrete actions that can be taken to improve ingredients analysis in a specific language.
   −
== Read those first
+
== Read this first ==
    
* [[Ingredients Extraction and Analysis]]: high level view and detailed description of all the steps
 
* [[Ingredients Extraction and Analysis]]: high level view and detailed description of all the steps
 
* [[Ingredients Analysis Quality]]: Metrics for ingredients analysis.
 
* [[Ingredients Analysis Quality]]: Metrics for ingredients analysis.
   −
== Determining the actions that will have the biggest impact to ingredients analysis in a specific language
+
== Determining the actions that will have the biggest impact to ingredients analysis in a specific language ==
   −
On the Open Food Facts web site, it is possible to see the result of ingredient analysis for a subset of product by adding /ingredients to the URL.
+
=== Finding out which ingredient we were not able to recognize ===
   −
e.g. on https://de.openfoodfacts.org you can add /ingredients to see all ingredients for products in Germany: https://de.openfoodfacts.org/ingredients
+
==== All ingredients ====
 +
 
 +
On the Open Food Facts web site, it is possible to see the result of ingredient analysis for a subset of product by adding /ingredients to the URL. It's also available in the "Explore products" drilldown button by selecting "ingredients".
 +
 
 +
e.g. on https://de.openfoodfacts.org you can add /ingredients to see all ingredients for products in Germany: https://de.openfoodfacts.org/ingredients (warning, it's a very long page that can make your browser hang)
 +
 
 +
Here is a more manageable result on a smaller subset (products sold in Germany that have a fair trade label): https://de.openfoodfacts.org/label/fairer-handel/ingredients
 +
 
 +
<pre>
 +
998 Inhaltsstoffe:
 +
 
 +
Inhaltsstoff Produkte *
 +
Zucker 185
 +
Kakao 167
 +
Emulgator 125
 +
E322 122
 +
Kakaobutter 114
 +
Kakaomasse 109
 +
Speiseöle und -fette 107
 +
Milcherzeugnisse 101
 +
Pflanzliche Öle und Fette 92
 +
Speisesalz 90
 +
Kakaopulver 78
 +
Aroma 74
 +
</pre>
 +
 
 +
If you go down the list, you will see ingredients in italics, with a * in the right column:
 +
 
 +
<pre>
 +
fr:carrageen-aus-biologischem-anbau 1 *
 +
kirschlikör-füllung 1 *
 +
natūrliche-aromen 1 *
 +
produkt-kann-spuren-von-erdnüssen 1 *
 +
teilweise-hydriertes-sojaöl 1 *
 +
milchpulvererzeugnis 1 *
 +
en:zucker 1 *
 +
fettarmes-kakaopuler 1 *
 +
</pre>
 +
 
 +
Those are ingredients that we did not recognize.
 +
 
 +
==== Ingredients stats ====
 +
 
 +
Adding ?stats=1 to the URL enables to see a summary count of known and unknown ingredients.
 +
 
 +
e.g. https://de.openfoodfacts.org/ingredients?stats=1
 +
 
 +
==== Unknown ingredients ====
 +
 
 +
You can then see only unknown ingredients by clicking on "unknown":
 +
 
 +
e.g. https://de.openfoodfacts.org/ingredients?status=unknown
 +
 
 +
Ingredients are ordered by the number of products they appear in, so it makes it easier to focus on the biggest problems first.
 +
 
 +
==== Filtering ingredients list ====
 +
 
 +
You can also add ?filter=something (or &filter=something if you already have another parameter in the url).
 +
 
 +
e.g. https://de.openfoodfacts.org/ingredients?status=unknown&filter=aroma
 +
 
 +
=== Reasons why we didn't recognize some ingredients ===
 +
 
 +
* The ingredient is not in the language of the ingredients list
 +
** The ingredients list in one language is put in the field for the ingredients list in another language
 +
*** This is often the case when the "main language" of the product was set to a wrong language, e.g. French for a German product.
 +
*** e.g. fr:carrageen-aus-biologischem-anbau (German ingredients in French ingredients list)
 +
** The ingredient list was not cut correctly and we have lists of ingredients in multiple languages instead of separated lists
 +
*** This is often the case when apps send us the result of the OCR of a big blob of text on the product label
 +
* The input ingredient list is incorrect (mispellings 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 formating (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)
 +
 
 +
=== Concrete steps to improve ingredients analysis ===
 +
 
 +
* Analyze the results of the ingredients analysis: https://de.openfoodfacts.org/ingredients?status=unknown
 +
** Classify the biggest problems you see
 +
*** Are many ingredients correct but missing in the taxonomy?
 +
**** Complete the ingredients taxonomy
 +
***** Verify if we have an existing entry in English, so that you can add a translation
 +
***** Else add a new entry in English + your target language (and possibly other languages too if you know the translation)
 +
*** Is there a particular structure that is not parsed correctly?
 +
**** e.g. multiple ingredients compounded together "Ingredient A and Ingredient B"
 +
**** e.g. an ingredient plus something that specify how it was processed, or a label "Organic something", "cooked sliced something"
 +
*** Open bugs with examples for the most common structures that we should better support
 +
**** e.g. https://github.com/openfoodfacts/openfoodfacts-server/issues/3020 for "raw something".
 +
**** bugs should be filed in https://github.com/openfoodfacts/openfoodfacts-server/issues , tag them with the "ingredients-analysis" label.

Navigation menu