Semi-supervised text mining for monitoring the news about the ESG performance of companies
- Author
- Samuel Borms, Kris Boudt (UGent) , Frederiek Van Holle and Joeri Willems
- Organization
- Abstract
- We present a general monitoring methodology to summarize news about predefined entities and topics into tractable time-varying indices. The approach embeds text mining techniques to transform news data into numerical data, which entails the querying and selection of relevant news articles and the construction of frequency- and sentiment-based indicators. Word embeddings are used to achieve maximally informative news selection and scoring. We apply the methodology from the viewpoint of a sustainable asset manager wanting to actively follow news covering environmental, social, and governance (ESG) aspects. In an empirical analysis, using a Dutch-written news corpus, we create news-based ESG signals for a large list of companies and compare these to scores from an external data provider. We find preliminary evidence of abnormal news dynamics leading up to downward score adjustments and of efficient portfolio screening.
Downloads
-
Publisher version.pdf
- full text (Published version)
- |
- open access
- |
- |
- 800.17 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-01GX3SPY4VR556GGAK87NXPYA3
- MLA
- Borms, Samuel, et al. “Semi-Supervised Text Mining for Monitoring the News about the ESG Performance of Companies.” Data Science for Economics and Finance : Methodologies and Applications, edited by Sergio Consoli et al., Springer, 2021, pp. 217–39, doi:10.1007/978-3-030-66891-4_10.
- APA
- Borms, S., Boudt, K., Holle, F. V., & Willems, J. (2021). Semi-supervised text mining for monitoring the news about the ESG performance of companies. In S. Consoli, D. Reforgiato Recupero, & M. Saisana (Eds.), Data science for economics and finance : methodologies and applications (pp. 217–239). https://doi.org/10.1007/978-3-030-66891-4_10
- Chicago author-date
- Borms, Samuel, Kris Boudt, Frederiek Van Holle, and Joeri Willems. 2021. “Semi-Supervised Text Mining for Monitoring the News about the ESG Performance of Companies.” In Data Science for Economics and Finance : Methodologies and Applications, edited by Sergio Consoli, Diego Reforgiato Recupero, and Michaela Saisana, 217–39. Cham: Springer. https://doi.org/10.1007/978-3-030-66891-4_10.
- Chicago author-date (all authors)
- Borms, Samuel, Kris Boudt, Frederiek Van Holle, and Joeri Willems. 2021. “Semi-Supervised Text Mining for Monitoring the News about the ESG Performance of Companies.” In Data Science for Economics and Finance : Methodologies and Applications, ed by. Sergio Consoli, Diego Reforgiato Recupero, and Michaela Saisana, 217–239. Cham: Springer. doi:10.1007/978-3-030-66891-4_10.
- Vancouver
- 1.Borms S, Boudt K, Holle FV, Willems J. Semi-supervised text mining for monitoring the news about the ESG performance of companies. In: Consoli S, Reforgiato Recupero D, Saisana M, editors. Data science for economics and finance : methodologies and applications. Cham: Springer; 2021. p. 217–39.
- IEEE
- [1]S. Borms, K. Boudt, F. V. Holle, and J. Willems, “Semi-supervised text mining for monitoring the news about the ESG performance of companies,” in Data science for economics and finance : methodologies and applications, S. Consoli, D. Reforgiato Recupero, and M. Saisana, Eds. Cham: Springer, 2021, pp. 217–239.
@incollection{01GX3SPY4VR556GGAK87NXPYA3,
abstract = {{We present a general monitoring methodology to summarize news about predefined entities and topics into tractable time-varying indices. The approach embeds text mining techniques to transform news data into numerical data, which entails the querying and selection of relevant news articles and the construction of frequency- and sentiment-based indicators. Word embeddings are used to achieve maximally informative news selection and scoring. We apply the methodology from the viewpoint of a sustainable asset manager wanting to actively follow news covering environmental, social, and governance (ESG) aspects. In an empirical analysis, using a Dutch-written news corpus, we create news-based ESG signals for a large list of companies and compare these to scores from an external data provider. We find preliminary evidence of abnormal news dynamics leading up to downward score adjustments and of efficient portfolio screening.}},
author = {{Borms, Samuel and Boudt, Kris and Holle, Frederiek Van and Willems, Joeri}},
booktitle = {{Data science for economics and finance : methodologies and applications}},
editor = {{Consoli, Sergio and Reforgiato Recupero, Diego and Saisana, Michaela}},
isbn = {{9783030668907}},
language = {{eng}},
pages = {{217--239}},
publisher = {{Springer}},
title = {{Semi-supervised text mining for monitoring the news about the ESG performance of companies}},
url = {{http://doi.org/10.1007/978-3-030-66891-4_10}},
year = {{2021}},
}
- Altmetric
- View in Altmetric