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

Differential patterns of health-related quality of life among low- and high-income cancer survivors in South Korea: a latent class analysis.

Quality of life research : an international journal of quality of life aspects of treatment, care and rehabilitation·2026
Same author

Mechanism by which a linoleic acid metabolite suppresses cancer cell growth by inhibiting mTOR.

Cell chemical biology·2026
Same author

Efficacy of Combined Gastric Peroral Endoscopic Myotomy and Transpyloric Stenting: A Case Report and Review of the Literature.

ACG case reports journal·2026
Same author

Long-term physical and mental health effects of unresolved disaster-related bereavement: evidence from an 8-year propensity score-matched cohort study.

European journal of psychotraumatology·2026
Same author

Optimization of enhancement-mode MIS-GaN HEMT with dual channel for simple process using TCAD simulation.

Scientific reports·2026
Same author

Protocol for in vitro transfection of mRNA-encapsulated lipid nanoparticles.

STAR protocols·2025

Related Experiment Video

Updated: Jul 2, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.8K

ESG2PreEM: Automated ESG grade assessment framework using pre-trained ensemble models.

Haein Lee1, Seon Hong Lee1, Heungju Park2

  • 1Department of Applied Artificial Intelligence/ Department of Human Artificial Intelligence Interaction, Sungkyunkwan University, 03063, Seoul, South Korea.

Heliyon
|February 26, 2024
PubMed
Summary

This study introduces an automated ESG rating strategy using natural language processing (NLP) and machine learning models like BERT and ALBERT. The developed framework achieved 80.79% accuracy, offering a novel approach to ESG assessment.

Keywords:
BERTESGEnsembleNatural language processing (NLP)Pretrained language model

More Related Videos

Author Spotlight: IntelliSleepScorer — A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research
04:54

Author Spotlight: IntelliSleepScorer — A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research

Published on: November 8, 2024

514
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

7.1K

Related Experiment Videos

Last Updated: Jul 2, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.8K
Author Spotlight: IntelliSleepScorer — A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research
04:54

Author Spotlight: IntelliSleepScorer — A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research

Published on: November 8, 2024

514
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

7.1K

Area of Science:

  • Business & Finance
  • Computer Science
  • Environmental Science

Background:

  • Environmental, Social, and Governance (ESG) criteria are crucial for business sustainability and firm value.
  • Existing ESG rating methods can be enhanced through automated text analysis.
  • The Refinitiv-Sustainable Leadership Monitor provides a comprehensive dataset for ESG classification.

Purpose of the Study:

  • To propose and validate an automated strategy for rating ESG criteria using text-based data.
  • To leverage advanced NLP models for autonomous ESG classification.
  • To compare the performance of the proposed framework against established ESG rating agencies.

Main Methods:

  • Collected data from the LexisNexis news archive for ESG classification.
  • Utilized Bidirectional Encoder Representations from Transformers (BERT), Robustly optimized BERT approach (RoBERTa), and A Lite BERT (ALBERT) models.
  • Implemented a voting ensemble model for autonomous ESG document categorization.
  • Validated the framework using companies from the Dow Jones Industrial Average (DJIA).

Main Results:

  • An ensemble model combining BERT and ALBERT achieved an accuracy of 80.79% with a batch size of 20.
  • The framework demonstrated reliable performance when validated against DJIA companies.
  • The automated ESG ratings showed comparability with those provided by MSCI.

Conclusions:

  • Sophisticated natural language processing (NLP) techniques can effectively extract valuable insights from large text datasets.
  • The proposed automated ESG rating strategy offers a viable and accurate alternative to traditional methods.
  • This research contributes to improving the robustness and efficiency of ESG assessment criteria.