Abstract

The increasing adoption of artificial intelligence (AI) in legal document analysis presents opportunities for improved contract interpretation and study. This research explores the use of BERTopic Dynamic Topic Modeling to analyze commercial contract clauses, identifying evolving trends in legal language and contractual structures. Using the Contract Understanding Atticus Dataset (CUAD), this research examines common contract clauses such as governing law, audit rights, and liability caps to uncover patterns across different industries, time periods, clause types, and jurisdictions. Using transformer-based embeddings, clustering techniques, and topic modeling, this research provides information on legal language shifts, the role of AI in contract review, and potential implications for legal practitioners and businesses. The findings demonstrate the ability of AI to improve contract analysis while highlighting key challenges in interpretability and legal transparency. This research contributes to the growing field of AI-driven legal analytics and suggests avenues for future research on automated contract evaluation.

Advisor

Musgrave, John

Department

Computer Science

Disciplines

Artificial Intelligence and Robotics | Data Science

Publication Date

2025

Degree Granted

Bachelor of Arts

Document Type

Senior Independent Study Thesis

Share

COinS
 

© Copyright 2025 Patrick Johnson