Zhang Haoyang, Zhang Dachuan, Wei Zhisheng, Li Yan, Wu Shaji, Mao Zhiheng, He Chunmeng, Ma Haorui, Zeng Xin, Xie Xiaoling, Kou Xingran, Zhang Bingwen
Department of Agrotechnology & Food Sciences, Wageningen University and Research, 6708 PB, Wageningen, the Netherlands.
Institute of Environmental Engineering, ETH Zurich, 8093, Zurich, Switzerland.
Curr Res Food Sci. 2023 Feb 22;6:100468. doi: 10.1016/j.crfs.2023.100468. eCollection 2023.
The Internet contains a wealth of public opinion on food safety, including views on food adulteration, food-borne diseases, agricultural pollution, irregular food distribution, and food production issues. To systematically collect and analyze public opinion on food safety in Greater China, we developed IFoodCloud, which automatically collects data from more than 3,100 public sources. Meanwhile, we constructed sentiment classification models using multiple lexicon-based and machine learning-based algorithms integrated with IFoodCloud that provide an unprecedented rapid means of understanding the public sentiment toward specific food safety incidents. Our best model's F1 score achieved 0.9737, demonstrating its great predictive ability and robustness. Using IFoodCloud, we analyzed public sentiment on food safety in Greater China and the changing trend of public opinion at the early stage of the 2019 Coronavirus Disease pandemic, demonstrating the potential of big data and machine learning for promoting risk communication and decision-making.
互联网上包含大量关于食品安全的公众意见，包括对食品掺假、食源性疾病、农业污染、食品分销不规范以及食品生产问题的看法。为了系统地收集和分析大中华地区关于食品安全的公众意见，我们开发了“食安云”（IFoodCloud），它能自动从3100多个公共来源收集数据。与此同时，我们使用多种基于词典和基于机器学习的算法与“食安云”相结合构建了情感分类模型，提供了一种前所未有的快速方式来了解公众对特定食品安全事件的情绪。我们最佳模型的F1分数达到了0.9737，证明了其强大的预测能力和稳健性。利用“食安云”，我们分析了大中华地区关于食品安全的公众情绪以及2019年冠状病毒病大流行早期公众舆论的变化趋势，展示了大数据和机器学习在促进风险沟通和决策方面的潜力。
