Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

ST-LDAW: A Topic-Model and Damped Weighted Least-Squares Method for Integrative Deconvolution of Single-Cell and Spatial Transcriptomics.

Interdisciplinary sciences, computational life sciences·2026
Same author

Tumor Heterogeneity in Gastrointestinal Cancer Based on Multimodal Data Analysis.

Genes·2024
Same author

Boosting Clear Cell Renal Carcinoma-Specific Drug Discovery Using a Deep Learning Algorithm and Single-Cell Analysis.

International journal of molecular sciences·2024
Same author

Autoformer-Based Model for Predicting and Assessing Wheat Quality Changes of Pesticide Residues during Storage.

Foods (Basel, Switzerland)·2023
Same author

Prediction of Food Safety Risk Level of Wheat in China Based on Pyraformer Neural Network Model for Heavy Metal Contamination.

Foods (Basel, Switzerland)·2023
Same author

FEDformer-Based Paddy Quality Assessment Model Affected by Toxin Change in Different Storage Environments.

Foods (Basel, Switzerland)·2023

Related Experiment Video

Updated: Sep 24, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.4K

An Entity Relationship Extraction Model Based on BERT-BLSTM-CRF for Food Safety Domain.

Qingchuan Zhang1,2, Menghan Li1,2, Wei Dong1,2

  • 1National Engineering Research Centre for Agri-Product Quality Traceability, Beijing Technology and Business University, Beijing 100048, China.

Computational Intelligence and Neuroscience
|May 9, 2022
PubMed
Summary

This study introduces a BERT-BLSTM-CRF model for extracting food safety relationships from public opinion data. This advanced method significantly improves the precision of identifying food safety issues, enhancing public health protection.

More Related Videos

Electronic Tongue Generating Continuous Recognition Patterns for Protein Analysis
08:46

Electronic Tongue Generating Continuous Recognition Patterns for Protein Analysis

Published on: September 16, 2014

7.9K
Detection of Foodborne Bacterial Pathogens from Individual Filth Flies
12:54

Detection of Foodborne Bacterial Pathogens from Individual Filth Flies

Published on: February 13, 2015

18.5K

Related Experiment Videos

Last Updated: Sep 24, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.4K
Electronic Tongue Generating Continuous Recognition Patterns for Protein Analysis
08:46

Electronic Tongue Generating Continuous Recognition Patterns for Protein Analysis

Published on: September 16, 2014

7.9K
Detection of Foodborne Bacterial Pathogens from Individual Filth Flies
12:54

Detection of Foodborne Bacterial Pathogens from Individual Filth Flies

Published on: February 13, 2015

18.5K

Area of Science:

  • Computational Linguistics
  • Food Science
  • Public Health

Background:

  • Timely management of food safety issues via online public opinion is crucial for mitigating impact and safeguarding health.
  • Constructing a food safety knowledge graph through entity relationship extraction from public opinion events aids in understanding food safety issues.
  • Few-shot learning presents challenges in extracting multi-entity relationships within food safety incident sentences.

Purpose of the Study:

  • To develop an effective method for extracting entity relationships in food safety public opinion events.
  • To construct a knowledge graph for the food safety field by identifying relationships between safety issues.
  • To address the limitations of few-shot learning in multi-entity relationship extraction for food safety incidents.

Main Methods:

  • A pipeline-type extraction method was employed to address multi-entity relationship challenges.
  • The Bidirectional Encoder Representation from Transformers (BERT) joined Bidirectional Long Short-Term Memory (BLSTM) network model (BERT-BLSTM) was utilized for initial entity relationship extraction.
  • An entity pair extraction model based on BERT-BLSTM and conditional random field (CRF), incorporating Chinese character features, was established.

Main Results:

  • The proposed BERT-BLSTM-CRF model demonstrated superior performance in entity relationship extraction.
  • Experimental results showed a precision increase of 3.29% to 23.25% compared to other deep neural network models.
  • The model's effectiveness was validated using a dedicated food public opinion events dataset.

Conclusions:

  • The BERT-BLSTM-CRF model offers a valid and rational approach for entity relationship extraction in food safety.
  • This method enhances the ability to discover relationships between food safety issues from public opinion data.
  • The findings support the timely identification and management of food safety concerns, contributing to public health protection.