TY - JOUR
T1 - Smartphone apps for tracking food consumption and recommendations
T2 - Evaluating artificial intelligence-based functionalities, features and quality of current apps
AU - Samad, Sabiha
AU - Ahmed, Fahmida
AU - Naher, Samsun
AU - Kabir, Muhammad Ashad
AU - Das, Anik
AU - Amin, Sumaiya
AU - Islam, Sheikh Mohammed Shariful
N1 - Funding Information:
The authors would like to thank Golam Sarwar Tuhin (CUET) for his help with the app ratings.
Publisher Copyright:
© 2022 The Author(s)
PY - 2022/9
Y1 - 2022/9
N2 - The advancement of artificial intelligence (AI) and the significant growth in the use of food consumption tracking and recommendation-related apps in the app stores have created a need for an evaluation system, as minimal information is available about the evidence-based quality and technological advancement of these apps. Electronic searches were conducted across three major app stores and the selected apps were evaluated by three independent raters. A total of 473 apps were found and 80 of them were selected for review based on inclusion and exclusion criteria. An app rating tool is devised to evaluate the selected apps. Our rating tool assesses the apps essential features, AI based advanced functionalities and software quality characteristics required for food consumption tracking and recommendations, as well as their usefulness to general users. The rating tool’s internal consistency, as well as inter- and intra-rater reliability among raters, are also calculated. Users’ comments from the app stores are collected and evaluated to better understand their expectations and perspectives. Following an evaluation of the assessed applications, design considerations that emphasize automation-based approaches using artificial intelligence are proposed. According to our assessment, most mobile apps in the app stores do not satisfy the overall requirements for tracking food consumption and recommendations. “Foodvisor” is the only app that can automatically recognise food items, and compute the recommended volume and nutritional information of that food item. However, these features need to be improvised in the food consumption tracking and recommendation apps. This study provides both researchers and developers with an insight into current state-of-the-art apps and design guidelines with necessary information on essential features and software quality characteristics for designing and developing a better app.
AB - The advancement of artificial intelligence (AI) and the significant growth in the use of food consumption tracking and recommendation-related apps in the app stores have created a need for an evaluation system, as minimal information is available about the evidence-based quality and technological advancement of these apps. Electronic searches were conducted across three major app stores and the selected apps were evaluated by three independent raters. A total of 473 apps were found and 80 of them were selected for review based on inclusion and exclusion criteria. An app rating tool is devised to evaluate the selected apps. Our rating tool assesses the apps essential features, AI based advanced functionalities and software quality characteristics required for food consumption tracking and recommendations, as well as their usefulness to general users. The rating tool’s internal consistency, as well as inter- and intra-rater reliability among raters, are also calculated. Users’ comments from the app stores are collected and evaluated to better understand their expectations and perspectives. Following an evaluation of the assessed applications, design considerations that emphasize automation-based approaches using artificial intelligence are proposed. According to our assessment, most mobile apps in the app stores do not satisfy the overall requirements for tracking food consumption and recommendations. “Foodvisor” is the only app that can automatically recognise food items, and compute the recommended volume and nutritional information of that food item. However, these features need to be improvised in the food consumption tracking and recommendation apps. This study provides both researchers and developers with an insight into current state-of-the-art apps and design guidelines with necessary information on essential features and software quality characteristics for designing and developing a better app.
KW - Smartphone apps
KW - Food nutrition
KW - Food consumption
KW - Food recommendations
KW - Apps evaluation
KW - Design guidelines
UR - http://www.scopus.com/inward/record.url?scp=85135390556&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85135390556&partnerID=8YFLogxK
U2 - 10.1016/j.iswa.2022.200103
DO - 10.1016/j.iswa.2022.200103
M3 - Review article
SN - 2667-3053
VL - 15
JO - Intelligent Systems with Applications
JF - Intelligent Systems with Applications
M1 - 200103
ER -