ESG2PreEM: Automated ESG grade assessment framework using pre-trained ensemble models
Incorporating environmental, social, and governance (ESG) criteria is essential for promoting sustainability in business and is considered a set of principles that can increase a firm’s value. This research proposes a strategy using text-based automated techniques to rate ESG. For autonomous classif...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-02-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844024024356 |
| _version_ | 1797267661506215936 |
|---|---|
| author | Haein Lee Seon Hong Lee Heungju Park Jang Hyun Kim Hae Sun Jung |
| author_facet | Haein Lee Seon Hong Lee Heungju Park Jang Hyun Kim Hae Sun Jung |
| author_sort | Haein Lee |
| collection | DOAJ |
| description | Incorporating environmental, social, and governance (ESG) criteria is essential for promoting sustainability in business and is considered a set of principles that can increase a firm’s value. This research proposes a strategy using text-based automated techniques to rate ESG. For autonomous classification, data were collected from the news archive LexisNexis and classified as E, S, or G based on the ESG materials provided by the Refinitiv-Sustainable Leadership Monitor, which has over 450 metrics. In addition, Bidirectional Encoder Representations from Transformers (BERT), Robustly optimized BERT approach (RoBERTa), and A Lite BERT (ALBERT) models were trained to accurately categorize preprocessed ESG documents using a voting ensemble model, and their performances were measured. The accuracy of the ensemble model utilizing BERT and ALBERT was found to be 80.79% with batch size 20. Additionally, this research validated the performance of the framework for companies included in the Dow Jones Industrial Average (DJIA) and compared it with the grade provided by Morgan Stanley Capital International (MSCI), a globally renowned ESG rating agency known for having the highest creditworthiness. This study supports the use of sophisticated natural language processing (NLP) techniques to attain important knowledge from large amounts of text-based data to improve ESG assessment criteria established by different rating agencies. |
| first_indexed | 2024-04-25T01:20:08Z |
| format | Article |
| id | doaj.art-3c1cb166ce9c4267880c665041b27f1c |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-04-25T01:20:08Z |
| publishDate | 2024-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-3c1cb166ce9c4267880c665041b27f1c2024-03-09T09:28:12ZengElsevierHeliyon2405-84402024-02-01104e26404ESG2PreEM: Automated ESG grade assessment framework using pre-trained ensemble modelsHaein Lee0Seon Hong Lee1Heungju Park2Jang Hyun Kim3Hae Sun Jung4Department of Applied Artificial Intelligence/ Department of Human Artificial Intelligence Interaction, Sungkyunkwan University, 03063, Seoul, South KoreaDepartment of Applied Artificial Intelligence/ Department of Human Artificial Intelligence Interaction, Sungkyunkwan University, 03063, Seoul, South KoreaSKK Business School, Sungkyunkwan University, 03063, Seoul, South KoreaDepartment of Interaction Science/ Department of Human Artificial Intelligence Interaction, Sungkyunkwan University, 03063, Seoul, South KoreaDepartment of Applied Artificial Intelligence, Sungkyunkwan University, 03063, Seoul, South Korea; Corresponding author.Incorporating environmental, social, and governance (ESG) criteria is essential for promoting sustainability in business and is considered a set of principles that can increase a firm’s value. This research proposes a strategy using text-based automated techniques to rate ESG. For autonomous classification, data were collected from the news archive LexisNexis and classified as E, S, or G based on the ESG materials provided by the Refinitiv-Sustainable Leadership Monitor, which has over 450 metrics. In addition, Bidirectional Encoder Representations from Transformers (BERT), Robustly optimized BERT approach (RoBERTa), and A Lite BERT (ALBERT) models were trained to accurately categorize preprocessed ESG documents using a voting ensemble model, and their performances were measured. The accuracy of the ensemble model utilizing BERT and ALBERT was found to be 80.79% with batch size 20. Additionally, this research validated the performance of the framework for companies included in the Dow Jones Industrial Average (DJIA) and compared it with the grade provided by Morgan Stanley Capital International (MSCI), a globally renowned ESG rating agency known for having the highest creditworthiness. This study supports the use of sophisticated natural language processing (NLP) techniques to attain important knowledge from large amounts of text-based data to improve ESG assessment criteria established by different rating agencies.http://www.sciencedirect.com/science/article/pii/S2405844024024356ESGNatural language processing (NLP)EnsemblePretrained language modelBERT |
| spellingShingle | Haein Lee Seon Hong Lee Heungju Park Jang Hyun Kim Hae Sun Jung ESG2PreEM: Automated ESG grade assessment framework using pre-trained ensemble models Heliyon ESG Natural language processing (NLP) Ensemble Pretrained language model BERT |
| title | ESG2PreEM: Automated ESG grade assessment framework using pre-trained ensemble models |
| title_full | ESG2PreEM: Automated ESG grade assessment framework using pre-trained ensemble models |
| title_fullStr | ESG2PreEM: Automated ESG grade assessment framework using pre-trained ensemble models |
| title_full_unstemmed | ESG2PreEM: Automated ESG grade assessment framework using pre-trained ensemble models |
| title_short | ESG2PreEM: Automated ESG grade assessment framework using pre-trained ensemble models |
| title_sort | esg2preem automated esg grade assessment framework using pre trained ensemble models |
| topic | ESG Natural language processing (NLP) Ensemble Pretrained language model BERT |
| url | http://www.sciencedirect.com/science/article/pii/S2405844024024356 |
| work_keys_str_mv | AT haeinlee esg2preemautomatedesggradeassessmentframeworkusingpretrainedensemblemodels AT seonhonglee esg2preemautomatedesggradeassessmentframeworkusingpretrainedensemblemodels AT heungjupark esg2preemautomatedesggradeassessmentframeworkusingpretrainedensemblemodels AT janghyunkim esg2preemautomatedesggradeassessmentframeworkusingpretrainedensemblemodels AT haesunjung esg2preemautomatedesggradeassessmentframeworkusingpretrainedensemblemodels |