Development of an Artificial Intelligence System to Monitor Digital Marketing of Unhealthy Food to Children: Research Protocol

Abstract

Objectives Unhealthy food marketing to children adversely affects their diet quality and health. The negative impacts of this marketing may be amplified on digital media, which allows industry to use artificial intelligence (AI) to market unhealthy food to children in covert ways. Health Canada is developing regulations to prohibit digital marketing of unhealthy food that appeals to children <13 years. However, reliance on adults to manually assess food marketing to children on digital media has limited understanding of key targets for policy and capacity to monitor policy adherence. To address these gaps, we are developing an AI system to monitor marketing of unhealthy food to children on digital media, including websites, YouTube, social media and mobile gaming apps. Methods Our web and mobile scrapers continuously collect marketing instances that may be viewed by individuals in Canada on websites and social media applications popular with children. This has allowed us to accumulate a database of > 615,000 marketing instances. The AI system extracts features from each marketing instance to determine whether foods are present, and if so, whether they are unhealthy according to Health Canada's standards (based on the presence of added saturated fat, added sodium and/or free sugars). Next, the AI system uses a supervised machine learning model to assess whether child appealing marketing techniques are present. In the final step, the system integrates all of the data collected to determine whether a given marketing instance features unhealthy foods and appeals to children. The system can be applied to monitor the extent and nature of digital food marketing to children internationally. It can also be retrained to monitor adherence to country-specific policy. Results This is a protocol paper so there are no results. Conclusions The AI system provides a scalable, objective and reproducible manner to identify digital marketing of unhealthy food that appeals to children across the digital marketing landscape. The system can assist researchers and policy makers to study children's exposure to digital marketing of unhealthy food and its impacts, and to monitor adherence to policy that restricts this marketing. Funding Sources Canadian Institutes of Health Research.

How frequently is alcohol advertised on television in Canada?: A cross-sectional study

“…2019 ), analyses of television ratings data ( Potvin Kent et al. 2023 ), audits of retail environments ( Minaker 2023 ), and the use of artificial intelligence tools in the assessment advertising data on a large scale ( Olstad et al. 2022 ), could be leveraged in this endeavor.…”

Revolutionising food advertising monitoring: a machine learning-based method for automated classification of food videos

“…To our knowledge, this is the first study to present results from automatic monitoring of food videos, highlighting the novelty of our study. In Canada, studies focus on automatic monitoring advertising on digital media (22,23) , proposing various steps for this approach, such as data collection, information extraction, marketing characteristics identification and nutritional information extraction (22,23) . The aim is to develop an AI-based system to monitor the marketing of unhealthy foods/brands to children on websites, social media and mobile gaming apps (22,23) , based on the CLICK monitoring structure proposed by WHO European Office for the Prevention and Control of Noncommunicable Diseases (18) .…”

“…Researchers in Canada and Australia are developing AI systems to monitor food marketing targeted at children (22)(23)(24) . The Canadian AI system focuses on monitoring digital platforms (22,23) , while the Australian machine learning (ML) algorithms include both digital and non-digital contexts (24) .…”

“…Researchers in Canada and Australia are developing AI systems to monitor food marketing targeted at children (22)(23)(24) . The Canadian AI system focuses on monitoring digital platforms (22,23) , while the Australian machine learning (ML) algorithms include both digital and non-digital contexts (24) . Although these studies are currently in the protocol phase, the outcomes of the AI-based system for automatic monitoring have not yet been published (22)(23)(24) .…”

“…The Canadian AI system focuses on monitoring digital platforms (22,23) , while the Australian machine learning (ML) algorithms include both digital and non-digital contexts (24) . Although these studies are currently in the protocol phase, the outcomes of the AI-based system for automatic monitoring have not yet been published (22)(23)(24) . Therefore, the primary aim of this study was to develop a ML-based method that could automatically identify and classify food and non-food ad videos by investigating deep neural networks.…”