The surveillance and prediction of food contamination using intelligent systems: a bibliometric analysis

Abstract

PurposeThis paper aims to report on the bibliometric research trends on the application of machine learning/intelligent systems in the prediction of food contamination and the surveillance of foodborne diseases.Design/methodology/approachIn this study, Web of Science (WoS) core collection database was used to retrieve publications from the year 1996–2021. Document types were classified according to country of origin, journals, citation and key research areas. The bibliometric parameters were analyzed using VOSviewer version 1.6.15 to visualize the international collaboration networks, citation density and link strength.FindingsA total of 516 articles across 6 document types were extracted with an average h-index of 51 from 10,570 citations. The leading journal in publications was Science of the Total Environment (3.6%) by Elsevier and the International Journal of Food Microbiology (2.5%). The United States of America (USA) (24%) followed by the People's Republic of China (17.2%) were the most influential countries in terms of publications. The top-cited articles in this study focused on themes such as contamination from packaging materials and on the strategies for preventing chemical contaminants in the food chain.Originality/valueThis report is significant because the public health field requires innovative strategies in forecasting foodborne disease outbreaks to advance effective interventions. Therefore, more collaboration need to be fostered, especially in developing nations regarding food safety research.