Future Research: AI & Unstructured Data

As I embark on my PhD studies, my objective is to push the boundaries of empirical accounting research by leveraging unstructured data and advanced analytical techniques. My future agenda is focused on using new data sources to answer fundamental questions in capital markets and corporate governance.

Application of NLP and Sentiment Analysis

I am particularly interested in applying machine learning and Natural Language Processing (NLP) for sentiment analysis of complex corporate narratives, such as MD&A sections and conference call transcripts. The goal is to develop more nuanced, real-time measures of corporate tone and risk exposure to predict future performance or misconduct, contributing to the literature on predictive analytics in accounting.

Leveraging LLMs for Regulatory Analysis

A novel avenue I am keen to explore involves using the advanced reasoning capabilities of Large Language Models (LLMs) to analyze regulatory filings. Inspired by work in journals like The Accounting Review and the Journal of Information Systems, I aim to build models that can help predict the likelihood of non-compliance with SEC regulations or identify inconsistencies in the application of GAAP codifications by parsing the complex textual data in 10-K reports. By leveraging social media and other digital platforms, I also intend to study the real-time dissemination of information and its effect on market behavior.

Ultimately, my goal is to develop new tools and uncover novel insights that enhance our understanding of corporate transparency and market efficiency in the digital age.