Prior Analyses

Predict recipe ratings

Given a pair of similar recipes, determine which one has higher average rating than the other.

• This task is designed particularly to help users with a specific dish or meal in mind, and who are trying to decide between several recipe options for that dish.
  • Work on this topic
    • Paper https://arxiv.org/pdf/1111.3919.pdf
    • Abstract http://arxiv.org/abs/1111.3919
    • Writeup http://www.npr.org/sections/thesalt/2012/11/19/165294248/could-nate-silver-predict-how-good-your-pumpkin-pie-will-be
    • Blog post http://www.ladamic.com/wordpress/?s=ingredient&searchsubmit=

Mapping food pairings

Identify patterns in the use of complementary ingredients.

• This task is designed to view how different cultures pair ingredients
  • Work on this topic
    • Paper http://www.nature.com/articles/srep00196
    • Writeup http://www.wired.com/2013/11/a-new-kind-of-food-science/
    • Blog post http://blog.bruggen.com/2013/12/fascinating-food-networks-in-neo4j.html

Use NLP to Interpret Recipes

The New York Times did a machine learning project using NLP to take raw text from a recipe and predict what the ingredients and quantities were.

• http://open.blogs.nytimes.com/2016/04/27/structured-ingredients-data-tagging/?_r=1
• https://github.com/NYTimes/ingredient-phrase-tagger?version=meter+at+0&module=meter-Links&pgtype=Blogs&contentId=&mediaId=&referrer=&priority=true&action=click&contentCollection=meter-links-click

Other projects

Recipe recommendation

• http://cs229.stanford.edu/proj2013/DengSafreno-TheRecipeLearner.pdf
• http://www.princeton.edu/~jmcohen/recipe-recommendation.pdf