TY - JOUR

T1 - Automatic classification of takeaway food outlet cuisine type using machine (deep) learning

AU - Bishop, Tom R P

AU - von Hinke, Stephanie

AU - Hollingsworth, Bruce

AU - Lake, Amelia A

AU - Brown, Heather

AU - Burgoine, Thomas

PY - 2021/12/15

Y1 - 2021/12/15

N2 - BACKGROUND AND PURPOSE: Researchers have not disaggregated neighbourhood exposure to takeaway ('fast-') food outlets by cuisine type sold, which would otherwise permit examination of differential impacts on diet, obesity and related disease. This is partly due to the substantial resource challenge of manual classification of unclassified takeaway outlets at scale. We describe the development of a new model to automatically classify takeaway food outlets, by 10 major cuisine types, based on business name alone.MATERIAL AND METHODS: We used machine (deep) learning, and specifically a Long Short Term Memory variant of a Recurrent Neural Network, to develop a predictive model trained on labelled outlets (n = 14,145), from an online takeaway food ordering platform. We validated the accuracy of predictions on unseen labelled outlets (n = 4,000) from the same source. RESULTS: Although accuracy of prediction varied by cuisine type, overall the model (or 'classifier') made a correct prediction approximately three out of four times. We demonstrated the potential of the classifier to public health researchers and for surveillance to support decision-making, through using it to characterise nearly 55,000 takeaway food outlets in England by cuisine type, for the first time.CONCLUSIONS: Although imperfect, we successfully developed a model to classify takeaway food outlets, by 10 major cuisine types, from business name alone, using innovative data science methods. We have made the model available for use elsewhere by others, including in other contexts and to characterise other types of food outlets, and for further development.

AB - BACKGROUND AND PURPOSE: Researchers have not disaggregated neighbourhood exposure to takeaway ('fast-') food outlets by cuisine type sold, which would otherwise permit examination of differential impacts on diet, obesity and related disease. This is partly due to the substantial resource challenge of manual classification of unclassified takeaway outlets at scale. We describe the development of a new model to automatically classify takeaway food outlets, by 10 major cuisine types, based on business name alone.MATERIAL AND METHODS: We used machine (deep) learning, and specifically a Long Short Term Memory variant of a Recurrent Neural Network, to develop a predictive model trained on labelled outlets (n = 14,145), from an online takeaway food ordering platform. We validated the accuracy of predictions on unseen labelled outlets (n = 4,000) from the same source. RESULTS: Although accuracy of prediction varied by cuisine type, overall the model (or 'classifier') made a correct prediction approximately three out of four times. We demonstrated the potential of the classifier to public health researchers and for surveillance to support decision-making, through using it to characterise nearly 55,000 takeaway food outlets in England by cuisine type, for the first time.CONCLUSIONS: Although imperfect, we successfully developed a model to classify takeaway food outlets, by 10 major cuisine types, from business name alone, using innovative data science methods. We have made the model available for use elsewhere by others, including in other contexts and to characterise other types of food outlets, and for further development.

KW - Classification

KW - Data science

KW - Cuisine type

KW - Universal Language Model Fine-tuning (ULMFiT)

KW - Takeaway (‘fast-’) food outlets

KW - Machine (deep) learning

U2 - 10.1016/j.mlwa.2021.100106

DO - 10.1016/j.mlwa.2021.100106

M3 - Journal article

C2 - 34977839

VL - 6

JO - Machine learning with applications

JF - Machine learning with applications

SN - 2666-8270

M1 - 100106

ER -