07/20/2023
By Mary Lou Kelly

The Department of Operations and Information Systems at the Manning School of Business invites you to attend a doctoral dissertation proposal by Cuibing Wu on “Executive Communications and Firm Performance: A Multimodal Deep Learning Analysis.”

Date: Friday, August 4th, 2023

Time: 10 – 11:30 a.m.

Location: Virtual (Zoom link)

Thesis/Dissertation Title: Executive Communications and Firm Performance: A Multimodal Deep Learning Analysis

Committee Members
1) Julie Zhang (Co-chair), Ph.D., Department of Operations & Information Systems, Manning School of Business, UMass Lowell
2) Xiao-bai (Bob) Li (Co-chair), Ph.D., Department of Operations & Information Systems, Manning School of Business, UMass Lowell
3) Shakil Quayes, Ph.D., Department of Economics, College of Fine Arts Humanities & Social Sciences, UMass Lowell

Abstract:
This dissertation proposal centers on CEO communications in public platforms and the resulting implications on firm performance leveraging multimodal deep learning methods to assess complex relationships. Four interconnected studies are presented, creating a comprehensive understanding of executive communication dynamics.

The first essay (Chapter 1) focuses on the impact of CEO interview videos shared on a social media platform on firms’ market value. A thorough analysis based on balanced panel data of firm-year observations provides substantial evidence of the power of social media as a tool for investor relations. The second essay (Chapter 2) delves into the non-verbal cues of CEO communications and examines CEO interview videos on YouTube to understand how multimodal features (facial emotional expressions, vocal features, and content informativeness) can serve as predictors for firm risk and volatility. The third essay (Chapter 3) broadens the analysis to cover the multimodal elements (verbal, vocal, and visual) of CEO interviews and the inter-modal inconsistency among these channels. Using a deep learning approach, this study refines stock volatility predictions using behavioral inconsistency and multimodal signals. The fourth essay (Chapter 4) investigates the dynamics of executive communications during earnings calls by examining the inconsistency of the vocal, textual, and emotional content between scripted presentations and Q&A sessions. This study also explores the relationships between CEOs’ personality traits and firm liquidity and returns to enrich our comprehension of how CEO communications impact firm performance.

All interested students and faculty members are invited to attend.