Quantitative Analysis of Japanese Integrated Reports by Using Word Embedding

Ryohsuke Tanaka () and Kazuhiko Tsuda ()
Additional contact information
Ryohsuke Tanaka: University of Tsukuba
Kazuhiko Tsuda: University of Tsukuba

A chapter in Economics and Finance Readings, 2025, pp 1-13 from Springer

Abstract: Abstract Currently, institutional ESG investors in Japan qualitatively evaluate the integrated reports of potential investment universe. They evaluate the completeness of descriptions regarding elements such as E (Environment), S (Social), and G (Governance). In fact, it is not easy to evaluate each integrated report, because there are differences in the descriptions among companies depending on their industries and businesses. Under such circumstances, this study proposes the method to calculate the volume of how much each description is mentioned in an integrated report. This method is applied to integrated reports issued by Japanese companies. As a result, by calculating the volume from the co-occurrence pairs using GPT-3.5, it is possible for ESG investors to quantitatively evaluate integrated reports.

Keywords: Integrated report; Word embedding; Text mining (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-981-96-6998-1_1

Ordering information: This item can be ordered from
http://www.springer.com/9789819669981

DOI: 10.1007/978-981-96-6998-1_1

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().