Data Science for Economics and Finance 2021
DOI: 10.1007/978-3-030-66891-4_10
|View full text |Cite
|
Sign up to set email alerts
|

Semi-supervised Text Mining for Monitoring the News About the ESG Performance of Companies

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 manag… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
7
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 11 publications
(7 citation statements)
references
References 20 publications
0
7
0
Order By: Relevance
“…Referring to Borms et al (2021) and Bhandari et al (2021), we used their identified keywords for our corresponding ESG dimensions and translated them into Chinese to set the original seed words. Then we read the CSR reports of 500 listed companies in our sample and extracted keywords related to the context to develop our seed words.…”
Section: Appendixmentioning
confidence: 99%
“…Referring to Borms et al (2021) and Bhandari et al (2021), we used their identified keywords for our corresponding ESG dimensions and translated them into Chinese to set the original seed words. Then we read the CSR reports of 500 listed companies in our sample and extracted keywords related to the context to develop our seed words.…”
Section: Appendixmentioning
confidence: 99%
“…To achieve the objective, an ESG index is constructed. Following Borms et al (2021), the index was created by utilizing data mining techniques and technology, particularly word frequency statistics from text mining, which show that attention would be brought to ESG if a news article about it were to be published. To the best of our knowledge, there is no universal definition of ESG.…”
Section: Methodology 41 Constructing the Country's Esg Indexmentioning
confidence: 99%
“…To the best of our knowledge, there is no universal definition of ESG. Therefore, this study uses seed terms from Borms et al (2021) to define the environmental, social, and governance elements. Using the Google search engine, the initial search comprised ESG keywords and the names of the ASEAN-5 countries to focus on the implementation of ESG.…”
Section: Methodology 41 Constructing the Country's Esg Indexmentioning
confidence: 99%
“…As the context and corpus of our research are based on the annual reports of the US manufacturing sector, we could not readily adapt the extant keywords developed from news reports by Borms et al (2021b, p. 226). However, we used the keywords identified by them as our seed words, and extended them using machine learning, NLP, and CATA, at large.…”
Section: Methods and Samplementioning
confidence: 99%