Predicting Adolescent Concern Toward Unhealthy Food Advertisements Using Deep Neural Networks With Explainable AI
DOI:
https://doi.org/10.63665/902kcg56Keywords:
XGBoost, Explainable AI, Adolescent Health, SHAP, LIME, Machine Learning, Food AdvertisementsAbstract
Predicting adolescent concern over unhealthy food advertisements is critical for promoting health awareness and guiding public policy. This study utilizes XGBoost, a gradient boosting machine learning model, to predict concern levels among adolescents based on demographic and behavioral features. Survey data from 1030 adolescents were collected, including age, parental education, and advertisement exposure types, such as celebrity endorsements and free toys. The model is trained with hyperparameter tuning and synthetic oversampling to handle imbalanced classes. Explainable AI techniques (LIME and SHAP) are applied to interpret feature importance, providing insights into which factors most influence adolescent concern. Results demonstrate that XGBoost achieves high predictive accuracy, offering an effective and interpretable solution for understanding and mitigating the impact of unhealthy food advertisements.
Downloads
References
[1] A. H. Alsharif, N. Z. M. Salleh, S. A. Al-Zahrani, and A. Khraiwish, ‘‘Consumer behaviour
to be considered in advertising: A systematic analysis and future agenda,’’ Behav. Sci., vol. 12,
no. 12, p. 472, Nov. 2022.
[2] D. A. Mathur, D. A. Mathur, and D. Gopalakrishnan, ‘‘Effect of food marketing on food
purchase request, eating behaviour and dental caries amongst 5–8 year old children belonging to
different socioeconomic backgrounds,’’ Global Pediatrics, vol. 6, Dec. 2023, Art. no. 100068.
[3] H. Jebeile, A. S. Kelly, G. O’Malley, and L. A. Baur, ‘‘Obesity in children and adolescents:
Epidemiology, causes, assessment, and management,’’ Lancet Diabetes Endocrinology, vol. 10,
no. 5, pp. 351–365, May 2022.
[4] R. Smith, B. Kelly, H. Yeatman, and E. Boyland, ‘‘Food marketing influences Children’s
attitudes, preferences and consumption: A systematic critical review,’’ Nutrients, vol. 11, no. 4,
p. 875, Apr. 2019.
[5] F. Folkvord, D. J. Anschütz, E. Boyland, B. Kelly, and M. Buijzen, ‘‘Food advertising and
eating behavior in children,’’ Current Opinion Behav. Sci., vol. 9, pp. 26–31, Jun. 2016.
[6] S. Kansal, A. Raj, N. Pedapanga, A. Worsley, and N. Rathi, ‘‘Indian adolescents’ perceptions
of packaged food and food labels—A qualitative inquiry,’’ Appetite, vol. 180, Jan. 2023, Art. no.
106342.
[7] L. Kakinami, S. Houle-Johnson, and J. J. McGrath, ‘‘Parental nutrition knowledge rather than
nutrition label use is associated with adiposity in children,’’ J. Nutrition Educ. Behav., vol. 48,
no. 7, pp. 461–467, Jul. 2016.
[8] N. Rathi, L. Riddell, and A. Worsley, ‘‘Food consumption patterns of adolescents aged
14–16 years in Kolkata, India,’’ Nutrition J., vol. 16, no. 1, pp. 1–12, Dec. 2017.
[9] M. M. Lane, E. Gamage, S. Du, D. N. Ashtree, A. J. McGuinness, S. Gauci, P. Baker, M.
Lawrence, C. M. Rebholz, B. Srour, M. Touvier, F. N. Jacka, A. O’Neil, T. Segasby, and W.
Marx, ‘‘Ultra-processed food exposure and adverse health outcomes: Umbrella review of
epidemiological metaanalyses,’’ BMJ, Feb. 2024, Art. no. e077310.
[10] L. M. Bodnar, A. R. Cartus, S. I. Kirkpatrick, K. P. Himes, E. H. Kennedy, H. N. Simhan,
W. A. Grobman, J. Y. Duffy, R. M. Silver, S. Parry, and A. I. Naimi, ‘‘Machine learning as a
strategy to account for dietary synergy: An illustration based on dietary intake and adverse
pregnancy outcomes,’’ Amer. J. Clin. Nutrition, vol. 111, no. 6, pp. 1235–1243, Jun. 2020.
[11] B. K. Chae, C. Sheu, and E. O. Park, ‘‘The value of data, machine learning, and deep
learning in restaurant demand forecasting: Insights and lessons learned from a large restaurant
chain,’’ Decis. Support Syst., vol. 184, Sep. 2024, Art. no. 114291.
[12] M. B. Rodrigues, V. P. Ferreira, R. M. Claro, A. P. B. Martins, S. Avila, and P. M. Horta,
‘‘Revolutionising food advertising monitoring: A machine learning-based method for automated
classification of food video
[13] T. A. Adjuik, N. A. A. Boi-Dsane, and B. A. Kehinde, ‘‘Enhancing dietary analysis: Using
machine learning for food caloric and health risk assessment,’’ J. Food Sci., vol. 89, no. 11, pp.
8006–8021, Nov. 2024.
[14] K. Psychogyios, L. Ilias, C. Ntanos, and D. Askounis, ‘‘Missing value imputation methods
for electronic health records,’’ IEEE Access, vol. 11, pp. 21562–21574, 2023.
[15] J. T. Hancock and T. M. Khoshgoftaar, ‘‘Survey on categorical data for neural networks,’’
J. Big Data, vol. 7, no. 1, Dec. 2020.
[16] M. Lu, Q. Hou, S. Qin, L. Zhou, D. Hua, X. Wang, and L. Cheng, ‘‘A stacking ensemble
model of various machine learning models for daily runoff forecasting,’’ Water, vol. 15, no. 7, p.
1265, Mar. 2023.
[17] T. Chilakala, ‘‘Artificial intelligence-based early detection of dengue using CBC data,’’ J.
Inf. Syst. Eng. Manage., vol. 10, no. 38s, pp. 304–321, Apr. 2025.
[18] I. D. Mienye and Y. Sun, ‘‘A survey of ensemble learning: Concepts, algorithms,
applications, and prospects,’’ IEEE Access, vol. 10, pp. 99129–99149, 2022.
[19] G. Biau, ‘‘Analysis of a random forests model,’’ J. Mach. Learn. Res., vol. 13, pp.
1063–1095, Jul. 2012.
[20] S. Simon, N. Kolyada, C. Akiki, M. Potthast, B. Stein, and N. Siegmund, ‘‘Exploring
hyperparameter usage and tuning in machine learning research,’’ in Proc. IEEE/ACM 2nd Int.
Conf. AI Eng. Softw. Eng. AI (CAIN), May 2023, pp. 68–79.
[21] D. Gaspar, P. Silva, and C. Silva, ‘‘Explainable AI for intrusion detection systems: LIME
and SHAP applicability on multi-layer perceptron,’’ IEEE Access, vol. 12, pp. 30164–30175,
2024.
[22] M. Nikam, A. Ranade, R. Patel, P. Dalvi, and A. Karande, ‘‘Explainable approach for
species identification using LIME,’’ in Proc. IEEE Bombay Sect. Signature Conf. (IBSSC), Dec.
2022, pp. 1–6.
[23] J. A. Ponce-Blandón, M. Pabón-Carrasco, R. Romero-Castillo, M. Romero-Martín, N.
Jiménez-Picón, and M. D. L. M. Lomas-Campos, ‘‘Effects of advertising on food consumption
preferences in children,’’ Nutrients, vol. 12, no. 11, p. 3337, Oct. 2020.
[24] J. L. Harris, J. L. Pomeranz, T. Lobstein, and K. D. Brownell, ‘‘A crisis in the marketplace:
How food marketing contributes to childhood obesity and what can be done,’’ Annu. Rev. Public
Health, vol. 30, no. 1, pp. 211–225, Apr. 2009.
[25] N. Pearson, S. J. Biddle, and T. Gorely, ‘‘Family correlates of fruit and vegetable
consumption in children and adolescents: A systematic review,’’ Public Health Nutrition, vol.
12, no. 2, pp. 267–283, Feb. 2009.
[26] B. Kelly, M. Cretikos, K. Rogers, and L. King, ‘‘The commercial food landscape: Outdoor
food advertising around primary schools in Australia,’’ Austral. New Zealand J. Public Health,
vol. 32, no. 6, pp. 522–528, Dec. 2008.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Authors
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
