Mapping ESG Trends by Distant Supervision of Neural Language Models
The integration of Environmental, Social and Governance (ESG) considerations into business decisions and investment strategies have accelerated over the past few years. It is important to quantify the extent to which ESG-related conversations are carried out by companies so that their impact on busi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Machine Learning and Knowledge Extraction |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-4990/2/4/25 |
| _version_ | 1797550335185649664 |
|---|---|
| author | Natraj Raman Grace Bang Armineh Nourbakhsh |
| author_facet | Natraj Raman Grace Bang Armineh Nourbakhsh |
| author_sort | Natraj Raman |
| collection | DOAJ |
| description | The integration of Environmental, Social and Governance (ESG) considerations into business decisions and investment strategies have accelerated over the past few years. It is important to quantify the extent to which ESG-related conversations are carried out by companies so that their impact on business operations can be objectively assessed. However, profiling ESG language is challenging due to its multi-faceted nature and the lack of supervised datasets. This research study aims to detect historical trends in ESG discussions by analyzing the transcripts of corporate earning calls. The proposed solution exploits recent advances in neural language modeling to understand the linguistic structure in ESG discourse. In detail, firstly we develop a classification model that categorizes the relevance of a text sentence to ESG. A pre-trained language model is fine-tuned on a small corporate sustainability reports dataset for this purpose. The semantic knowledge encoded in this classification model is then leveraged by applying it to the sentences in the conference transcripts using a novel distant-supervision approach. Extensive empirical evaluations against various pretraining techniques demonstrate the efficacy of the proposed transfer learning framework. Our analysis indicates that in the last 5 years, nearly 15% of the discussions during earnings calls pertained to ESG, implying that ESG factors are integral to business strategy. |
| first_indexed | 2024-03-10T15:27:50Z |
| format | Article |
| id | doaj.art-b54fda6bee0b48219fe55e3d68f59bef |
| institution | Directory Open Access Journal |
| issn | 2504-4990 |
| language | English |
| last_indexed | 2024-03-10T15:27:50Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machine Learning and Knowledge Extraction |
| spelling | doaj.art-b54fda6bee0b48219fe55e3d68f59bef2023-11-20T17:54:03ZengMDPI AGMachine Learning and Knowledge Extraction2504-49902020-10-012445346810.3390/make2040025Mapping ESG Trends by Distant Supervision of Neural Language ModelsNatraj Raman0Grace Bang1Armineh Nourbakhsh2J.P. Morgan AI Research, London E14 5JP, UKBloomberg LP, New York, NY 10017, USAJ.P. Morgan AI Research, New York, NY 10179, USAThe integration of Environmental, Social and Governance (ESG) considerations into business decisions and investment strategies have accelerated over the past few years. It is important to quantify the extent to which ESG-related conversations are carried out by companies so that their impact on business operations can be objectively assessed. However, profiling ESG language is challenging due to its multi-faceted nature and the lack of supervised datasets. This research study aims to detect historical trends in ESG discussions by analyzing the transcripts of corporate earning calls. The proposed solution exploits recent advances in neural language modeling to understand the linguistic structure in ESG discourse. In detail, firstly we develop a classification model that categorizes the relevance of a text sentence to ESG. A pre-trained language model is fine-tuned on a small corporate sustainability reports dataset for this purpose. The semantic knowledge encoded in this classification model is then leveraged by applying it to the sentences in the conference transcripts using a novel distant-supervision approach. Extensive empirical evaluations against various pretraining techniques demonstrate the efficacy of the proposed transfer learning framework. Our analysis indicates that in the last 5 years, nearly 15% of the discussions during earnings calls pertained to ESG, implying that ESG factors are integral to business strategy.https://www.mdpi.com/2504-4990/2/4/25NLPpre-trained embeddingstransfer learningESGsustainability reports |
| spellingShingle | Natraj Raman Grace Bang Armineh Nourbakhsh Mapping ESG Trends by Distant Supervision of Neural Language Models Machine Learning and Knowledge Extraction NLP pre-trained embeddings transfer learning ESG sustainability reports |
| title | Mapping ESG Trends by Distant Supervision of Neural Language Models |
| title_full | Mapping ESG Trends by Distant Supervision of Neural Language Models |
| title_fullStr | Mapping ESG Trends by Distant Supervision of Neural Language Models |
| title_full_unstemmed | Mapping ESG Trends by Distant Supervision of Neural Language Models |
| title_short | Mapping ESG Trends by Distant Supervision of Neural Language Models |
| title_sort | mapping esg trends by distant supervision of neural language models |
| topic | NLP pre-trained embeddings transfer learning ESG sustainability reports |
| url | https://www.mdpi.com/2504-4990/2/4/25 |
| work_keys_str_mv | AT natrajraman mappingesgtrendsbydistantsupervisionofneurallanguagemodels AT gracebang mappingesgtrendsbydistantsupervisionofneurallanguagemodels AT arminehnourbakhsh mappingesgtrendsbydistantsupervisionofneurallanguagemodels |