investigating the healthiness of internet-sourced recipes: implications for meal planning and...

27
Investigating the Healthiness of Internet-Sourced Recipes Implications for Meal Planning and Recommender Systems Dr. Christoph Trattner Department of New Media Technology

Upload: christoph-trattner

Post on 15-Apr-2017

148 views

Category:

Internet


1 download

TRANSCRIPT

Page 1: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

Investigating the Healthiness of Internet-Sourced Recipes

Implications for Meal Planning and Recommender SystemsDr. Christoph Trattner Department of New Media Technology

Page 2: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

Context

Trattner, C. and Elsweiler, D. Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems. In Proc. WWW’17.

@ctrattner @delsweil

Page 3: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

Why is research on (online) food useful?

Food is one the main concepts that shapes how good we feel and how healthy we are.

According to the WHO, within the last three decades overweight and obesity in the EU population rised dramatically > 30% (especially for the younger generation

Resulting in a cost of approx. € 81 billion a year to help people with chronic diseases

Page 4: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

…A government’s response to increasing incidence of lifestyle-related illnesses, such as obesity, has been to

encourage people to cook for themselves…

Cooking inspiration:

Page 5: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems
Page 6: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

Questions RQ1: How healthy are Internet-Sourced recipes with

respect to recognized standards? RQ2: How do user interactions such as ratings, comments

or social bookmarks people apply to recipes relate to the healthiness of recipe content?

RQ3: How healthy are the recipes recommended by standard recommendation algorithms when applied to the food recommendation problem?

RQ4: Can we improve standard recommender algorithms in terms of making the recommendations they offer more healthy?

Question?

Page 7: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

Dataset

Page 8: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

Nutrition Facts

Basic statistics:

60,983 recipes 125,762 users rating 155,769 users bookmarking 1,032,226 ratings 17,190,534 bookmarks

Dataset: Allrecipes.com

Page 9: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

Allrecipes.com popularity

According to Alexa.com

Page 10: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

Questions RQ1: How healthy are Internet-Sourced recipes with

respect to recognized standards? RQ2: How do user interactions such as ratings, comments or

social bookmarks people apply to recipes relate to the healthiness of recipe content?

RQ3: How healthy are the recipes recommended by standard recommendation algorithms when applied to the food recommendation problem?

RQ4: Can we improve standard recommender algorithms in terms of making the recommendations they offer more healthy?

Question?

Page 11: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

Determining the healthiness

FSA food health criteria

Usda. cook more often at home. available at http://www.choosemyplate.gov/weight-management-calories/weight-management/better-choices/cook-home.html. Last accessed on 20.6.2016. 2011.

Page 12: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

WHO

food

hea

lth c

riter

ia

J. Who and F. E. Consultation. Diet, nutrition and the prevention of chronic diseases. World Health Organ TechRep Ser, 916(i-viii), 2003.

Determining the healthiness

Page 13: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

Internet recipe healthiness

Internet recipes are quite unhealthy!

Page 14: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

User perception

Results when asking users (n=32) how healthy categories are on Allrecipes.com

(Kappa κ = .165, z = 42, p < .001)

Page 15: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

Internet recipesvs

TV chef recipesvs

Supermarket ready meals

Comparing recipes

Page 16: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

Internet recipe health comparison

Trattner, C. Elsweiler, D. and Simon, H. Estimating the Healthiness of Internet Recipes: A Cross-Sectional Study. Frontiers in Public Health, 2017.

Page 17: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

WHO

crite

riaFS

A cr

iteriaHealthiness over time

There is not much change over time!

Page 18: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

Questions RQ1: How healthy are Internet-Sourced recipes with respect

to recognized standards? RQ2: How do user interactions such as ratings, comments

or social bookmarks people apply to recipes relate to the healthiness of recipe content?

RQ3: How healthy are the recipes recommended by standard recommendation algorithms when applied to the food recommendation problem?

RQ4: Can we improve standard recommender algorithms in terms of making the recommendations they offer more healthy?

Question?

Page 19: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

Spearman rank correlation,* p < .05, ** p < .01, *** p < .001

Results: Interaction Correlation

Page 20: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

Questions RQ1: How healthy are Internet-Sourced recipes with respect

to recognized standards? RQ2: How do user interactions such as ratings, comments or

social bookmarks people apply to recipes relate to the healthiness of recipe content?

RQ3: How healthy are the recipes recommended by standard recommendation algorithms when applied to the food recommendation problem?

RQ4: Can we improve standard recommender algorithms in terms of making the recommendations they offer more healthy?

Question?

Page 21: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

*** p < .001

Results: Recommender

Libray: LibRecEval: 10 fold-cross validation

∆=𝑡𝑟𝑎𝑖𝑛−𝑝𝑟𝑒𝑑

Std. recommender produce unhealthy

suggestions!

Page 22: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

Questions RQ1: How healthy are Internet-Sourced recipes with respect

to recognized standards? RQ2: How do user interactions such as ratings, comments or

social bookmarks people apply to recipes relate to the healthiness of recipe content?

RQ3: How healthy are the recipes recommended by standard recommendation algorithms when applied to the food recommendation problem?

RQ4: Can we improve standard recommender algorithms in terms of making the recommendations they offer more healthy?

Question?

Page 23: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

Pearson correlations (= rho) between MAP and nDCG and FSA and WHO health scores (on user level) for individual algorithms.

Sign. high correlation

Correlation

Page 24: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

Post-Filter scoring functions

Linear combinations as discussed in Elsweiler et al. (2015) did not work

Re-ranking for health

D. Elsweiler, M. Harvey, B. Ludwig, and A. Said. Bringing the "healthy" into food recommenders. In Proc. ofDRMS’15., pages 33–36.

Page 25: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

Results: Recommender (2)

Note: similar results with bookmarks

Std. recommender can be enhanced

to produce healthy suggestions!

Page 26: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems

OK, that’s it!

for now ;)

Take home:

Internet-sourced recipes are not per

se healthy

Page 27: Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems