FOOD SCIENCE ›› 2021, Vol. 42 ›› Issue (7): 35-44.doi: 10.7506/spkx1002-6630-20200505-027

• Basic Research • Previous Articles     Next Articles

Data Mining Model for Food Safety Incidents Based on Structural Analysis and Semantic Similarity

CHEN Mo, ZHANG Jingxiang, HU Enhua, WU Linhai, ZHANG Yi   

  1. (1. College of Economics and Management, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China; 2. School of Science, Jiangnan University, Wuxi 214122, China; 3. School of Biotechnology, Jiangnan University, Wuxi 214122, China; 4. Institute for Food Safety Risk Management, School of Business, Jiangnan University, Wuxi 214122, China)
  • Online:2021-04-15 Published:2021-05-17

Abstract: Food safety concerns public health and the stability of society. In this paper, we analyzed the characteristics of the food safety incidents (FSIs), including spatial distribution, food categories, risk factors, and supply chain links, reported by mainstream media in China. Based on our analysis, we constructed a semantic template for text data related to FSIs. Moreover, we introduced a strategy of multi-layer and multi-level semantic structure of rank (MMSS-Rank) algorithm to measure the similarity between the collected food safety data and the semantic template, and then calculated the overall scores and selected an appropriate threshold to determine the accuracy of the FSI data. Supporting vector machine and semantic structure template are adopted to conduct the classification accuracy comparison via data extraction and cleansing.Results showed that compared with the traditional methods, MMSS-Rank was an efficient and robust method for identifying large-scale FSI data with higher accuracy and recall rate.

Key words: food safety incidents; semantic analysis; semantic structure template; big data

CLC Number: