What You Say Your Strategy Is and Why It Matters: Natural Language Processing of Unstructured Text

Abstract

This study explores how new text analysis tools can be used in strategic management research that examines unstructured textual data. We build on two established natural language processing (NLP) techniques, vector space models and topic modeling, to create text-based measures of several core constructs in strategy – namely strategic change, positioning, and focus. These techniques are applied to the entire sample of 50,506 business descriptions in 10-K annual reports from 1997 to 2016. Results show that these new methods produce innovative yet meaningful measures of firm strategy which open many previously unexplored avenues for research to strategy scholars. The study advances emerging strategy research utilizing text analysis methods, demonstrates that NLP techniques can overcome the limitations of traditional text analysis methods such as keyword counts and mapping analysis, and provides a template for how other machine learning techniques could be introduced into strategy.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 16 citations exist upstream.