Measuring digitalization capabilities using machine learning

Jinglan Yang, Jianghuai Liu, Zheng Yao and Chaoqun Ma

Research in International Business and Finance, 2024, vol. 70, issue PB

Abstract: By applying a widely used machine learning technique called natural language processing (NLP) to unstructured text from annual reports, we create a new, multi-dimensional measure that captures the degree of digitalization capabilities of sensing, seizing, and reconfiguring. We construct a digitalization capabilities dictionary using one of the latest NLP techniques—the word embedding model—for 36,200 firm-year observations over the period 2010–2021. Moreover, we show the top- and bottom-ranked listed firms in China by digitalization capabilities. Finally, we illustrate how these new measures can generate novel insights into the relationship between the type of digitalization capabilities and firm performance through regression analysis, furthering our understanding of the digitalization–performance relationship. That is, digitalization capabilities function as a double-edged sword that may help or hurt firm performance.

Keywords: Digitalization capabilities; Annual reports; Natural language processing; word2vec; Financial performance (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0275531924001739
Full text for ScienceDirect subscribers only

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:eee:riibaf:v:70:y:2024:i:pb:s0275531924001739

DOI: 10.1016/j.ribaf.2024.102380

Access Statistics for this article

Research in International Business and Finance is currently edited by T. Lagoarde Segot

More articles in Research in International Business and Finance from Elsevier
Bibliographic data for series maintained by Catherine Liu ().