research-article

“Tell Me Why”: using natural language justifications in a recipe recommender system to support healthier food choices

Authors:

Alain D. Starke,

Giovanni Semeraro,

Christoph TrattnerAuthors Info & Claims

User Modeling and User-Adapted Interaction, Volume 34, Issue 2

Pages 407 - 440

https://doi.org/10.1007/s11257-023-09377-8

Published: 24 October 2023 Publication History

Abstract

Users of online recipe websites tend to prefer unhealthy foods. Their popularity undermines the healthiness of traditional food recommender systems, as many users lack nutritional knowledge to make informed food decisions. Moreover, the presented information is often unrelated to nutrition or difficult to understand. To alleviate this, we present a methodology to generate natural language justifications that emphasize the nutritional content, health risks, or benefits of recommended recipes. Our framework takes a user and two recipes as input and produces an automatically generated natural language justification as output, based on the user’s characteristics and the recipes’ features, following a knowledge-based recommendation approach. We evaluated our methodology in two crowdsourcing studies. In Study 1 (

N = 502

), we compared user food choices for two personalized recommendation approaches, based on either a (1) single-style justification or (2) comparative justification was shown, using a no justification baseline. The recommendations were either popularity-based or health-aware, the latter based on the health and nutritional needs of the user. We found that comparative justification styles were effective in supporting choices for our health-aware recommendations, confirming the impact of our methodology on food choices. In Study 2 (

N = 504

), we used the same methodology to compare the effectiveness of eight different comparative justification strategies. We presented pairs of recipes twice to users: once without and once with a pairwise justification. Results indicated that justifications led to significantly healthier choices for first course meals, while strategies that compared food features and emphasized health risks, benefits, and a user’s lifestyle were most effective, catering to health-related choice motivations.

References

[1]

Ajzen, I., Fishbein, M.: The influence of attitudes on behavior. In: The Handbook of Attitudes. Volume 1: Basic Principles, pp. 173–221. Routledge, London (2005)

[2]

Ajzen, I.: The theory of planned behavior. Organizational Behavior and Human Decision Processes. Theories of Cognitive Self-Regulation 50(2), 179–211 (1991).

[3]

Ateş H Merging theory of planned behavior and value identity personal norm model to explain pro-environmental behaviors Sustain. Prod. Consump. 2020 24 169-180

[4]

Bandura A Social Foundations of Thought and Action: A Social Cognitive Theory 1986 New York, NY Prentice-Hall

[5]

Bandura A Self-Efficacy: The Exercise of Control 1997 New York, NY Freeman

[6]

Bettman JR, Luce MF, and Payne JW Constructive consumer choice processes J. Consum. Res. 1998 25 3 187-217

[7]

Bialkova S and van Trijp HC An efficient methodology for assessing attention to and effect of nutrition information displayed front-of-pack Food Qual. Prefer. 2011 22 6 592-601

[8]

Bialkova S, Grunert KG, Juhl HJ, Wasowicz-Kirylo G, Stysko-Kunkowska M, and van Trijp HC Attention mediates the effect of nutrition label information on consumers’ choice. Evidence from a choice experiment involving eye-tracking Appetite 2014 76 66-75

[9]

Biran, O., Cotton, C.: Explanation and justification in machine learning: a survey. In: IJCAI-17 Workshop on Explainable AI (XAI), p. 8 (2017)

[10]

Bonaiuto F, De Dominicis S, Ganucci Cancellieri U, Crano WD, Ma J, and Bonaiuto M Italian food? sounds good! made in Italy and Italian sounding effects on food products’ assessment by consumers Front. Psychol. 2021 12

[11]

Cadario R and Chandon P Which healthy eating nudges work best? A meta-analysis of field experiments Mark. Sci. 2020 39 3 465-486

Digital Library

[12]

Cena, F., Likavec, S., Rapp, A.: Real world user model: Evolution of user modeling triggered by advances in wearable and ubiquitous computing: State of the art and future directions. Information Systems Frontiers, 1–26 (2018a). Cited By 0; Article in Press

Digital Library

[13]

Cena, F., Rapp, A., Musto, C., Lops, P.: Towards a conceptual model for holistic recommendations. In: Adjunct Publication of the 26th Conference on User Modeling, Adaptation and Personalization. UMAP ’18, pp. 207–210. Association for Computing Machinery, New York, NY (2018b).

Digital Library

[14]

Cena F, Rapp A, Musto C, and Semeraro G Generating recommendations from multiple data sources: a methodological framework for system design and its application IEEE Access 2020 8 183430-183447

[15]

Chen, L., Wang, F.: Explaining Recommendations based on Feature Sentiments in Product Reviews. In: Proceedings of the 22nd International Conference on Intelligent User Interfaces, pp. 17–28 (2017). ACM

[16]

Cramer H, Evers V, Ramlal S, Van Someren M, Rutledge L, Stash N, Aroyo L, and Wielinga B The effects of transparency on trust and acceptance of a content-based art recommender User Model. User-Adap. Inter. 2008 18 5 455-496

Digital Library

[17]

Dallacker M, Hertwig R, and Mata J The frequency of family meals and nutritional health in children: a meta-analysis Obes. Rev. 2018 19 5 638-653

[18]

DiSalvo, C., Sengers, P., Brynjarsdóttir, H.: Mapping the landscape of sustainable hci. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. CHI ’10, pp. 1975–1984. Association for Computing Machinery, New York, NY, USA (2010)

[19]

Ekstrand, M.D., Willemsen, M.C.: Behaviorism is not enough: better recommendations through listening to users. In: Proceedings of the 10th ACM Conference on Recommender Systems, pp. 221–224 (2016)

[20]

Elahi, M., Ge, M., Ricci, F., Fernández-Tobías, I., Berkovsky, S., David, M., et al.: Interaction design in a mobile food recommender system. In: CEUR Workshop Proceedings (2015). CEUR-WS

[21]

Elahi, M., Ge, M., Ricci, F., Massimo, D., Berkovsky, S.: Interactive food recommendation for groups. In: 8th ACM Conference on Recommender Systems (RecSys) (2014). CEUR Workshop Proceedings

[22]

Elsweiler, D., Hauptmann, H., Trattner, C.: Food recommender systems. In: Recommender Systems Handbook, pp. 871–925. Springer, New York, NY, USA (2022)

[23]

Elsweiler, D., Hauptmann, H., Trattner, C.: Food recommender systems. In: Ricci, F., Rokach, L., Shapira, B. (eds.) Recommender Systems Handbook, pp. 871–925. Springer, New York, NY (2022).

[24]

Elsweiler, D., Trattner, C., Harvey, M.: Exploiting food choice biases for healthier recipe recommendation. In: Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. SIGIR ’17, pp. 575–584. Association for Computing Machinery, New York, NY, USA (2017).

Digital Library

[25]

Freyne, J., Berkovsky, S.: Intelligent food planning: personalized recipe recommendation. In: Proceedings of the 15th International Conference on Intelligent User Interfaces, pp. 321–324 (2010)

[26]

Friedrich G and Zanker M A taxonomy for generating explanations in recommender systems AI Mag. 2011 32 3 90-98

Digital Library

[27]

Furst T, Connors M, Bisogni CA, Sobal J, and Falk LW Food choice: a conceptual model of the process Appetite 1996 26 3 247-266

[28]

Gkika, S., Lekakos, G.: The persuasive role of explanations in recommender systems. In: BCSS@ PERSUASIVE, pp. 59–68 (2014)

[29]

Gomez-Uribe CA and Hunt N The netflix recommender system: algorithms, business value, and innovation ACM Trans. Manag. Inform. Syst. (TMIS) 2015 6 4 1-19

Digital Library

[30]

Gutjar S, de Graaf C, Kooijman V, de Wijk RA, Nys A, Ter Horst GJ, and Jager G The role of emotions in food choice and liking Food Res. Int. 2015 76 216-223

[31]

Hagger MS Non-conscious processes and dual-process theories in health psychology Health Psychol. Rev. 2016 10 4 375-380 PMID: 27718880

[32]

Herlocker J and Konstan J Content-independent task-focused recommendation IEEE Internet Comput. 2001 5 6 40-47

Digital Library

[33]

Hors-Fraile, S., Benjumea, F.J.N., Hernández, L.C., Ruiz, F.O., Fernandez-Luque, L.: Design of two combined health recommender systems for tailoring messages in a smoking cessation app (2016). arXiv:1608.07192

[34]

Hors-Fraile S, Candel MJ, Schneider F, Malwade S, Nunez-Benjumea FJ, Syed-Abdul S, Fernandez-Luque L, and de Vries H Applying collective intelligence in health recommender systems for smoking cessation: A comparison trial Electronics 2022 11 8 1219

[35]

Howard, S., Adams, J., White, M.: Nutritional content of supermarket ready meals and recipes by television chefs in the united kingdom: cross sectional study. BMJ345 (2012)

[36]

Ilich, J.Z., Vollono, J.A., Brownbill, R.A.: Impact of nutritional knowledge on food choices and dietary intake of college students. Journal of the American Dietetic Association 99(9, Supplement), 89 (1999).

[37]

Jannach D, Zanker M, Felfernig A, and Friedrich G Recommender Systems: An Introduction 2010 New York, NY Cambridge University Press

Digital Library

[38]

Johnson, H., Johnson, P.: Explanation Facilities and Interactive Systems. In: Proceedings of the 1st International Conference on Intelligent User Interfaces, pp. 159–166 (1993). ACM

[39]

Jun J, Kang J, and Arendt SW The effects of health value on healthful food selection intention at restaurants: considering the role of attitudes toward taste and healthfulness of healthful foods Int. J. Hosp. Manag. 2014 42 85-91

[40]

Kahneman D Thinking 2011 Straus and Giroux, New York, NY, USA Fast and Slow. Farrar

[41]

Kalnikaitė V, Bird J, and Rogers Y Decision-making in the aisles: informing, overwhelming or nudging supermarket shoppers? Pers. Ubiquit. Comput. 2013 17 6 1247-1259

Digital Library

[42]

Köster EP Diversity in the determinants of food choice: a psychological perspective Food Qual. Prefer. 2009 20 2 70-82

[43]

Kroese FM, Marchiori DR, and de Ridder DT Nudging healthy food choices: a field experiment at the train station J. Public Health 2016 38 2 133-137

[44]

Lee JH, Hwang J, and Mustapha A Popular ethnic foods in the united states: a historical and safety perspective Comp. Rev. Food Sci. Food Saf. 2014 13 1 2-17

[45]

Leipold, N., Madenach, M., Schäfer, H., Lurz, M., Terzimehic, N., Groh, G., Böhm, M., Gedrich, K., Krcmar, H.: Nutrilize a personalized nutrition recommender system: an enable study. HealthRecSys@ RecSys 2216, 24–29 (2018)

[46]

Levenstein H The American response to Italian food, 1880–1930 Food Foodways 1985 1 1–2 1-23

[47]

Locke EA and Latham GP Building a practically useful theory of goal setting and task motivation. A 35-year odyssey Am. Psychol. 2002 57 9 705-717

[48]

McFadden D Zarembka P Conditional logit analysis of qualitative choice behavior Frontiers in Econometrics 1973 New York Academic Press 105-142

[49]

Munson, S.A., Consolvo, S.: Exploring goal-setting, rewards, self-monitoring, and sharing to motivate physical activity. In: 2012 6th International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth) and Workshops, pp. 25–32 (2012).

[50]

Musto, C., de Gemmis, M., Lops, P., Semeraro, G.: Generating post hoc review-based natural language justifications for recommender systems. User Modeling and User-Adapted Interaction, pp. 1–45 (2020)

[51]

Musto, C., Trattner, C., Starke, A., Semeraro, G.: Towards a knowledge-aware food recommender system exploiting holistic user models. In: Kuflik, T., Torre, I., Burke, R., Gena, C. (eds.) Proceedings of the 28th ACM Conference on User Modeling, Adaptation and Personalization, UMAP 2020, Genoa, Italy, July 12-18, 2020, pp. 333–337. Association for Computing Machinery, New York, NY, USA (2020).

Digital Library

[52]

Musto C, Narducci F, Lops P, de Gemmis M, and Semeraro G Linked open data-based explanations for transparent recommender systems Int. J. Hum. Comput. Stud. 2019 121 93-107

[53]

Musto C, Polignano M, Semeraro G, de Gemmis M, and Lops P Myrror: a platform for holistic user modeling User Model. User-Adap. Inter. 2020 30 3 477-511

Digital Library

[54]

Musto C, Narducci F, Polignano M, De Gemmis M, Lops P, and Semeraro G Myrrorbot: A digital assistant based on holistic user models for personalized access to online services ACM Trans. Inform. Syst. (TOIS) 2021 39 4 1-34

Digital Library

[55]

Neumark-Sztainer D, MacLehose R, Loth K, Fulkerson JA, Eisenberg ME, and Berge J What’s for dinner? Types of food served at family dinner differ across parent and family characteristics Public Health Nutr. 2014 17 1 145-155

[56]

Nunes I and Jannach D A systematic review and taxonomy of explanations in decision support and recommender systems User Model. User-Adap. Inter. 2017 27 3–5 393-444

Digital Library

[57]

Organization, W.H.: Diet, Nutrition, and the Prevention of Chronic Diseases: Report of a Joint WHO/FAO Expert Consultation, vol. 916. World Health Organization, Geneva (2003)

[58]

Orji R and Moffatt K Persuasive technology for health and wellness: State-of-the-art and emerging trends Health Inform. J. 2018 24 1 66-91

[59]

Petty RE, Heesacker M, and Hughes JN The elaboration likelihood model: Implications for the practice of school psychology J. Sch. Psychol. 1997 35 2 107-136

[60]

Pinder C, Vermeulen J, Cowan BR, and Beale R Digital behaviour change interventions to break and form habits ACM Trans. Comput. Hum. Interact. 2018

Digital Library

[61]

Polignano M, Narducci F, Iovine A, Musto C, De Gemmis M, and Semeraro G Healthassistantbot: a personal health assistant for the Italian language IEEE Access 2020 8 107479-107497

[62]

Prochaska JO and Velicer WF The transtheoretical model of health behavior change Am. J. Health Promot. 1997 12 1 38-48

[63]

Rapp, A., Tirassa, M., Tirabeni, L.: Rethinking technologies for behavior change: A view from the inside of human change. ACM Trans. Comput.-Hum. Interact. (2019).

Digital Library

[64]

Reiter E and Dale R Building Natural Language Generation Systems 2000 New York, NY Cambridge University Press

[65]

Rosenstock IM Historical origins of the health belief model Health Educ. Monogr. 1974 2 4 328-335

[66]

Schäfer, H., Hors-Fraile, S., Karumur, R.P., Calero Valdez, A., Said, A., Torkamaan, H., Ulmer, T., Trattner, C.: Towards health (aware) recommender systems. In: Proceedings of the 2017 International Conference on Digital Health, pp. 157–161 (2017)

[67]

Schäfer, H., Willemsen, M.C.: Rasch-based tailored goals for nutrition assistance systems. In: Proceedings of the 24th International Conference on Intelligent User Interfaces, pp. 18–29 (2019)

[68]

Schunk, D.: Self-efficacy for learning and performance. In: Annual Conference of the American Educational Research Association, pp. 1–24 (1996).

[69]

Sinha, R., Swearingen, K.: The Role of Transparency in Recommender Systems. In: CHI’02 Extended Abstracts on Human Factors in Computing Systems, pp. 830–831 (2002). ACM

[70]

Starke, A., Asotic, E., Trattner, C.: “serving each user”: Supporting different eating goals through a multi-list recommender interface. In: Fifteenth ACM Conference on Recommender Systems, pp. 124–132 (2021)

[71]

Starke, A.D., Trattner, C.: Promoting healthy food choices online: A case for multi-list recommender systems. In: HEALTHI’21: Joint Proceedings of ACM IUI 2021 Workshops (2021)

[72]

Starke, A.D., Willemsen, M.C., Snijders, C.: With a little help from my peers: Depicting social norms in a recommender interface to promote energy conservation. In: Proceedings of the 25th International Conference on Intelligent User Interfaces, pp. 568–578 (2020)

[73]

Starke, A.: The effectiveness of advice solicitation and social peers in an energy recommender system. In: 6th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems, IntRS 2019, pp. 65–71 (2019). CEUR

[74]

Starke AD, Willemsen MC, and Trattner C Nudging healthy choices in food search through visual attractiveness Front. Artif. Intell. 2021 4 20

[75]

Stowell, E., Lyson, M.C., Saksono, H., Wurth, R.C., Jimison, H., Pavel, M., Parker, A.G.: Designing and evaluating mhealth interventions for vulnerable populations: A systematic review. In: Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems. CHI ’18, pp. 1–17. Association for Computing Machinery, New York, NY, USA (2018).

Digital Library

[76]

Symeonidis P, Nanopoulos A, and Manolopoulos Y Providing justifications in recommender systems IEEE Trans. Syst. Man Cybern.-A: Syst. Humans 2008 38 6 1262-1272

Digital Library

[77]

Taylor, D., Bury, M., Campling, N., Carter, S., Garfied, S., Newbould, J., Rennie, T.: A Review of the use of the Health Belief Model (HBM), the Theory of Reasoned Action (TRA), the Theory of Planned Behaviour (TPB) and the Trans-Theoretical Model (TTM) to study and predict health related behaviour change. Technical report, University of London (2007)

[78]

Tintarev N and Masthoff J Ricci F, Rokach L, Shapira B, and Kantor PB Designing and evaluating explanations for recommender systems Recommender Systems Handbook 2011 New York, NY Springer 479-510

[79]

Tintarev N and Masthoff J Evaluating the effectiveness of explanations for recommender systems UMUAI 2012 22 4–5 399-439

Digital Library

[80]

Tran TNT, Atas M, Felfernig A, and Stettinger M An overview of recommender systems in the healthy food domain J. Intell. Inform. Syst. 2018 50 3 501-526

Digital Library

[81]

Trattner, C., Elsweiler, D.: Food recommendations. In: Collaborative Recommendations: Algorithms. Practical Challenges and Applications, pp. 653–685. World Scientific, UK (2019)

[82]

Trattner, C., Elsweiler, D.: Investigating the healthiness of internet-sourced recipes: implications for meal planning and recommender systems. In: Proceedings of the 26th International Conference on World Wide Web, pp. 489–498 (2017)

[83]

Trichopoulou A, Martínez-González MA, Tong TY, Forouhi NG, Khandelwal S, Prabhakaran D, Mozaffarian D, and de Lorgeril M Definitions and potential health benefits of the Mediterranean diet: views from experts around the world BMC Med. 2014 12 1 1-16

[84]

Tudoran A, Olsen SO, and Dopico DC The effect of health benefit information on consumers health value, attitudes and intentions Appetite 2009 52 3 568-579

[85]

Wardle J, Parmenter K, and Waller J Nutrition knowledge and food intake Appetite 2000 34 3 269-275

[86]

Willett WC The mediterranean diet: science and practice Public Health Nutr. 2006 9 1a 105-110

[87]

Zhu, H., Huberman, B., Luon, Y.: To switch or not to switch: understanding social influence in online choices. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 2257–2266 (2012)

[88]

Zimmerman BJ Self-efficacy: an essential motive to learn Contemp. Educ. Psychol. 2000 25 1 82-91

[89]

Zulkosky K Self-efficacy: a concept analysis Nurs. Forum 2009 44 2 93-102

Cited By

Starke AVrijenhoek SMichiels LKruse JTintarev N(2024)NORMalize 2024: The Second Workshop on Normative Design and Evaluation of Recommender SystemsProceedings of the 18th ACM Conference on Recommender Systems10.1145/3640457.3687103(1242-1244)Online publication date: 8-Oct-2024
https://dl.acm.org/doi/10.1145/3640457.3687103

Recommendations

Does Journaling Encourage Healthier Choices?: Analyzing Healthy Eating Behaviors of Food Journalers
DH '18: Proceedings of the 2018 International Conference on Digital Health

Past research has shown the benefits of food journaling in promoting mindful eating and healthier food choices. However, the links between journaling and healthy eating have not been thoroughly examined. Beyond caloric restriction, do journalers ...
Examining the User Evaluation of Multi-List Recommender Interfaces in the Context of Healthy Recipe Choices
Multi-list recommender systems have become widespread in entertainment and e-commerce applications. Yet, extensive user evaluation research is missing. Since most content is optimized toward a user’s current preferences, this may be problematic in ...
Online Recommender System for Personalized Nutrition Advice
RecSys '17: Proceedings of the Eleventh ACM Conference on Recommender Systems

The general recommendations for addressing non-communicable diseases, which are responsible for two thirds of deaths globally, are mainly related to lifestyle changes, such as diet and physical activity. Challenges with encouraging healthy diets include ...

Comments

Information & Contributors

Information

Published In

cover image User Modeling and User-Adapted Interaction

User Modeling and User-Adapted Interaction Volume 34, Issue 2

Apr 2024

221 pages

Issue’s Table of Contents

© The Author(s) 2023.

Publisher

Kluwer Academic Publishers

United States

Publication History

Published: 24 October 2023

Accepted: 21 July 2023

Received: 02 June 2022

Author Tags

Qualifiers

Research-article

Funding Sources

Norges Forskningsråd

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 22 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Starke AVrijenhoek SMichiels LKruse JTintarev N(2024)NORMalize 2024: The Second Workshop on Normative Design and Evaluation of Recommender SystemsProceedings of the 18th ACM Conference on Recommender Systems10.1145/3640457.3687103(1242-1244)Online publication date: 8-Oct-2024
https://dl.acm.org/doi/10.1145/3640457.3687103

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents