Machine Learning Approaches to Facial and Text Analysis: Discovering CEO Oral Communication Styles

Prithwiraj  Choudhury; Dan  Wang; Natalie A. Carlson; Tarun   Khanna

Article | Strategic Management Journal

Machine Learning Approaches to Facial and Text Analysis: Discovering CEO Oral Communication Styles

by Prithwiraj Choudhury, Dan Wang, Natalie A. Carlson and Tarun Khanna

Abstract

We demonstrate how a novel synthesis of three methods—(1) unsupervised topic modeling of text data to generate new measures of textual variance, (2) sentiment analysis of text data, and (3) supervised ML coding of facial images with a cutting-edge convolutional neural network algorithm—can shed light on questions related to CEO oral communication. With videos and corresponding transcripts of interviews with emerging market CEOs, we employ this synthesis of methods to discover five distinct communication styles that incorporate both verbal and nonverbal aspects of communication. Our data are comprised of interviews that represent unedited expressions and content, making them especially suitable as data sources for the measurement of an individual’s communication style. We then perform a proof-of-concept analysis, correlating CEO communication styles to M&A outcomes, highlighting the value of combining text and videographic data to define styles. We also discuss the benefits of using our methods versus current research methods.

Keywords: CEOs; communication style; Machine learning; Spoken Communication; Nonverbal Communication; Personal Characteristics; Analysis; Performance;

Format: Print

Find at Harvard

Citation:

Choudhury, Prithwiraj, Dan Wang, Natalie A. Carlson, and Tarun Khanna. "Machine Learning Approaches to Facial and Text Analysis: Discovering CEO Oral Communication Styles." Strategic Management Journal 40, no. 11 (November 2019): 1705–1732.

While there is evidence about labor market discrimination based on race, religion, and gender, we know little about whether physical appearance leads to discrimination in labor market outcomes. We deploy a randomized experiment on 1,000 respondents in India between April and May 2020 to investigate how “looks” affect labor market outcomes. Using machine learning and computer face rendering techniques, we simulate North, South, and Northeastern Indian faces and randomize two waves of treatments where we attach faces with otherwise identical CVs. However, the second wave also contains a vignette where we provide respondents with information about the incidence of discrimination. We focus on Northeastern Indian faces that resemble those in China to focus on the potential for discrimination that has historically been present in anecdotal accounts. While we do not find evidence of discrimination against Northeastern faces in the first wave, we do so in the second among those who do not see the vignette. We provide suggestive evidence that these results are consistent with the presence of homophily under limited attention.

Pallak Seth, Group CEO of PDS Multinational Fashions, is contemplating options to bring better collaboration across his global apparel supply chain platform. PDS, a group of 50-plus subsidiary companies, each led by its own CEO and with different apparel industry specialties, has grown rapidly over the past decade, yet the industry is increasingly competitive and challenges remain constant. Looking for ways to reach the Group’s 2023 goals of $2 billion in revenue, Seth and his executive board are considering two ways to increase collaboration and reward performance: a joint P&L approach to drive partnerships across the subsidiaries and an employee stock option plan, to unlock value across the Group.

Faculty & Research

Machine Learning Approaches to Facial and Text Analysis: Discovering CEO Oral Communication Styles

Abstract

Citation:

About the Authors

More from these Authors