ABSTRACT
Food recommenders have the potential to positively influence the eating habits of users. To achieve this, however, we need to understand how healthy recommendations are and the factors which influence this. Focusing on two approaches from the literature (single item and daily meal plan recommendation) and utilizing a large Internet sourced dataset from Allrecipes.com, we show how algorithmic solutions relate to the healthiness of the underlying recipe collection. First, we analyze the healthiness of Allrecipes.com recipes using nutritional standards from the World Health Organisation and the United Kingdom Food Standards Agency. Second, we investigate user interaction patterns and how these relate to the healthiness of recipes. Third, we experiment with both recommendation approaches. Our results indicate that overall the recipes in the collection are quite unhealthy, but this varies across categories on the website. Users in general tend to interact most often with the least healthy recipes. Recommender algorithms tend to score popular items highly and thus on average promote unhealthy items. This can be tempered, however, with simple post-filtering approaches, which we show by experiment are better suited to some algorithms than others. Similarly, we show that the generation of meal plans can dramatically increase the number of healthy options open to users. One of the main findings is, nevertheless, that the utility of both approaches is strongly restricted by the recipe collection. Based on our findings we draw conclusions how researchers should attempt to make food recommendation systems promote healthy nutrition.
- Fsa nutrient and food based guidelines for uk institutions. available at http://www.food.gov.uk/sites/default/files/multimedia/pdfs/nutrientinstitution.pdf. last accessed on 20.6.2016. 2007.Google Scholar
- 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.Google Scholar
- Fsa. guide to creating a front of pack (fop) nutrition label for pre-packed products sold through retail outlets. available at https://www.gov.uk/government/uploads/system/uploads/attachment_data/file/300886/2902158_FoP_Nutrition_2014.pdf. last accessed on 27.6.2016. 2014.Google Scholar
- Allrecipe.com press report. available at http://press.recipes.com/. last accessed on 20.6.2016. 2016.Google Scholar
- Allrecipe.co.uk press report. available at http://allrecipes.co.uk/news.aspx. last accessed on 20.6.2016. 2016.Google Scholar
- Esha, nutrition labeling software. available at http://www.esha.com/. last accessed on 20.6.2016. 2016.Google Scholar
- S. Abbar, Y. Mejova, and I. Weber. You tweet what you eat: Studying food consumption through twitter. In Proc. of CHI'15. Google ScholarDigital Library
- P. Achananuparp and I. Weber. Extracting food substitutes from food diary via distributional similarity. arXiv preprint arXiv:1607.08807, 2016.Google Scholar
- M. De Choudhury and S. S. Sharma. Characterizing dietary choices, nutrition, and language in food deserts via social media. In Proc. of CSCW '16. Google ScholarDigital Library
- T. De Pessemier, S. Dooms, and L. Martens. A food recommender for patients in a care facility. In Proc. of RecSys'13, pages 209--212. ACM. Google ScholarDigital Library
- D. Elsweiler and M. Harvey. Towards automatic meal plan recommendations for balanced nutrition. In Proc. of RecSys'15, pages 313--316. ACM. Google ScholarDigital Library
- D. Elsweiler, M. Harvey, B. Ludwig, and A. Said. Bringing the "healthy" into food recommenders. In Proc. of DRMS'15., pages 33--36.Google Scholar
- J. Freyne and S. Berkovsky. Recommending food: Reasoning on recipes and ingredients. In Proc. of UMAP'10, pages 381--386. Google ScholarDigital Library
- M. Ge, F. Ricci, and D. Massimo. Health-aware food recommender system. In Proc. of RecSys '15, pages 333--334. Google ScholarDigital Library
- T. Griffiths. Gibbs sampling in the generative model of latent dirichlet allocation. 2002.Google Scholar
- F. Harrell. Regression modeling strategies: with applications to linear models, logistic and ordinal regression, and survival analysis. Springer, 2015. Google ScholarCross Ref
- M. Harvey, B. Ludwig, and D. Elsweiler. Learning user tastes: a first step to generating healthy meal plans? In Proc. of LIFESTYLE'12, page 18.Google Scholar
- S. Howard, J. Adams, M. White, et al. Nutritional content of supermarket ready meals and recipes by television chefs in the united kingdom: cross sectional study. BMJ, 345, 2012.Google Scholar
- Y. Hu, Y. Koren, and C. Volinsky. Collaborative filtering for implicit feedback datasets. In Proc. of ICDM'08, pages 263--272. Ieee. Google ScholarDigital Library
- C. Kim and J. Kim. A recommendation algorithm using multi-level association rules. In Proc. of WI'03, pages 524--527. IEEE. Google ScholarDigital Library
- K.-J. Kim and C.-H. Chung. Tell me what you eat, and i will tell you where you come from: A data science approach for global recipe data on the web. IEEE Access, 4:8199--8211, 2016.Google ScholarCross Ref
- T. Kusmierczyk, C. Trattner, and K. Nørvåg. Temporal patterns in online food innovation. In Proc. of WWW'15 Companion. Google ScholarDigital Library
- T. Kusmierczyk, C. Trattner, and K. Nørvåg. Temporality in online food recipe consumption and production. In Proc. of WWW'15. Google ScholarDigital Library
- T. Kusmierczyk, C. Trattner, and K. Nørvåg. Understanding and predicting online food recipe production patterns. In Proceedings of the 27th ACM Conference on Hypertext and Social Media, pages 243--248. ACM, 2016. Google ScholarDigital Library
- S. Larrain, C. Trattner, D. Parra, E. Graells-Garrido, and K. Nørvåg. Good times bad times: A study on recency effects in collaborative filtering for social tagging. In Proc. of RecSys'15, pages 269--272. Google ScholarDigital Library
- Y. Mejova, H. Haddadi, A. Noulas, and I. Weber.# foodporn: Obesity patterns in culinary interactions. In Proceedings of the 5th International Conference on Digital Health 2015, pages 51--58. ACM, 2015. Google ScholarDigital Library
- X. Ning and G. Karypis. Slim: Sparse linear methods for top-n recommender systems. In Proc. of ICDM'11, pages 497--506. IEEE. Google ScholarDigital Library
- S. Rendle, C. Freudenthaler, Z. Gantner, and L. Schmidt-Thieme. Bpr: Bayesian personalized ranking from implicit feedback. In Proc. of UIAI'09, pages 452--461. AUAI Press. Google ScholarDigital Library
- F. Ricci, L. Rokach, and B. Shapira. Introduction to recommender systems handbook. Springer, 2011. Google ScholarCross Ref
- M. Rokicki, E. Herder, and E. Demidova. What's on my plate: Towards recommending recipe variations for diabetes patients. Proc. of UMAP'15 LBRS, 2015.Google Scholar
- M. Rokicki, E. Herder, T. Kusmierczyk, and C. Trattner. Plate and prejudice: Gender differences in online cooking. In Proc. of UMAP'16, pages 207--215. Google ScholarDigital Library
- G. Sacks, M. Rayner, and B. Swinburn. Impact of front-of-pack traffic-light-nutrition labelling on consumer food purchases in the uk. Health promotion international, 24(4):344--352, 2009.Google Scholar
- A. Said and A. Bellogíın. You are what you eat! tracking health through recipe interactions. In Proc. of RSWeb'14.Google Scholar
- B. Sarwar, G. Karypis, J. Konstan, and J. Riedl. Item-based collaborative filtering recommendation algorithms. In Proc. of WWW'01, pages 285--295. ACM. Google ScholarDigital Library
- E. P. Schneider, E. E. McGovern, C. L. Lynch, and L. S. Brown. Do food blogs serve as a source of nutritionally balanced recipes' an analysis of 6 popular food blogs. Journal of nutrition education and behavior, 45(6):696--700, 2013.Google Scholar
- C.-Y. Teng, Y.-R. Lin, and L. A. Adamic. Recipe recommendation using ingredient networks. In Proc. of WebSci'12, pages 298--307. Google ScholarDigital Library
- M. Thelwall, K. Buckley, and G. Paltoglou. Sentiment strength detection for the social web. JASIST, 63(1):163--173, 2012. Google ScholarDigital Library
- C. Trattner and D. Elsweiler. Estimating the heathiness of internet recipes: A cross sectional study. Frontiers in Public Health, 2017.Google Scholar
- C. Trattner, D. Kowald, P. Seitlinger, T. Ley, and S. Kopeinik. Modeling activation processes in human memory to predict the use of tags in social bookmarking systems. J. Web Science, 2(1):1--16, 2016.Google ScholarCross Ref
- C. Trattner, T. Kusmierczyk, and K. Nørvåg. FOODWEB - studying food consumption and production patterns on the web. ERCIM News, 2016(104), 2016.Google Scholar
- C. Wagner and L. M. Aiello. Men eat on mars, women on venus? an empirical study of food-images. In Proc. of WebSci'15 Posters. Google ScholarDigital Library
- C. Wagner, P. Singer, and M. Strohmaier. The nature and evolution of online food preferences. EPJ Data Science, 3(1):1--22, 2014.Google ScholarCross Ref
- R. West, R. W. White, and E. Horvitz. From cookies to cooks: Insights on dietary patterns via analysis of web usage logs. In Proc. of WWW'13, pages 1399--1410. Google ScholarDigital Library
- J. Who and F. E. Consultation. Diet, nutrition and the prevention of chronic diseases. World Health Organ Tech Rep Ser, 916(i-viii), 2003.Google Scholar
Index Terms
- Investigating the Healthiness of Internet-Sourced Recipes: Implications for Meal Planning and Recommender Systems
Recommendations
On the Relations Between Cooking Interests, Hobbies and Nutritional Values of Online Recipes: Implications for Health-Aware Recipe Recommender Systems
UMAP '17: Adjunct Publication of the 25th Conference on User Modeling, Adaptation and PersonalizationIn this paper, we investigate differences between recipes uploaded by users and recipes bookmarked by users. The results indicate that uploaded recipes outperform bookmarked recipes in terms of healthiness. Further, health scores and nutritional values ...
Investigating serendipity in recommender systems based on real user feedback
SAC '18: Proceedings of the 33rd Annual ACM Symposium on Applied ComputingOver the past several years, research in recommender systems has emphasized the importance of serendipity, but there is still no consensus on the definition of this concept and whether serendipitous items should be recommended is still not a well-...
Comments