Web-Crawling Architecture in Accounting and Finance Research

ABSTRACT

We examine the practice of web-crawling architecture through two logics: combinational logic (CL) and sequential logic (SL) and adopt a test ground on the relationship between price informativeness and corporate social responsibility (CSR) news releases among publicly listed former unicorns. Our results show that the CL approach is more optimal than the SL approach regarding time consumption, storage efficiency and data accuracy, which suggest that CSR media exposures have substantial influence on price informativeness. Both positive (optimistic) and negative (pessimistic)-toned CSR information increases price informativeness. We find that the Diction wordlist displays higher classification accuracy when analyzing CSR news release.

KEYWORDS:

• Web-crawling architecture
• combinational logic
• sequential logic
• corporate social responsibility
• price informativeness

Acknowledgments

We are grateful to the anonymous reviewers of EAA Annual Congress 2020 and AFAANZ Conference 2020 for their constructive comments and suggestions on earlier versions of this paper. We would like to express our gratitude to the seminars attendees at the University of Western Australia and Waseda University.