Using Text Mining to Read Integrated Reports in Banking Industry

Visualizing hot topics such as ESG and DX


September 21, 2022

  • Rie Nakada
  • Satoshi Osanai
  • Atsushi Yamato
  • Kiyoka Ishikawa


◆In recent years, interest in ESG related information published by corporations has been increasing in response to the rapid expansion of ESG investment. As the disclosure of ESG related information is expanded, how to analyze textual information related to ESG is one of the new challenges. In this report, we attempted to visualize hot topics using text mining and machine learning on integrated reports of banking industry.

◆Based on the analyses, we were able to extract differences in awareness of the ESG field and related subjects by bank type, as well as priority items in management strategies. Specifically, the city bank group's strong awareness of environmental issues and its emphasis on addressing digitalization, and regional banks' awareness of contributing to local communities and economics (the first-tier regional banks) were noted. On the other hand, the low frequency of digital technology-related words appearing in the second-tier regional banks search suggests that these banks are behind in digitalization.

◆Text mining and machine learning technologies will be among most useful tools for analyzing non-financial information, including ESG related information, which will continue to grow in importance in the future.

Daiwa Institute of Research Ltd. reserves all copyrights of this content.
Copyright permission of Daiwa Institute of Research Ltd. is required in case of any reprint, translation, adaptation or abridgment under the copyright law. It is illegal to reprint, translate, adapt, or abridge this material without the permission of Daiwa Institute of Research Ltd., and to quote this material represents a failure to abide by this act. Legal action may be taken for any copyright infringements. The organization name and title of the author described above are as of today.