Integrating Artificial Intelligence and Social Network Systems to Enhance Contracting Efficiency

View at publisher Summarise with VIRAT
Authors: Haiyan Sally Xie, Swetha Yallapu, Pranshoo Solanki, C.‐J. Richard Shi
Cited by: 0
References: 7

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Traditional contracting processes often experience delays, miscommunication, and inefficiencies due to fragmented information and limited predictive capabilities. This paper proposes a framework to enhance transparency, accelerate decision-making, and optimize resource allocation throughout the contracting lifecycle. In this architecture, Legal-BERT (Bidirectional Encoder Representations from Transformers) extracts domain-specific semantic representations from legal documents, which are then processed by a Large Language Model for contextual reasoning and predictive analytics. Simultaneously, a Knowledge Graph organizes contractual entities into a structured relational map, enabling real-time query, compliance checks, and interpretability. The methodology combines Artificial Intelligence (AI) models for contract risk assessment with social network analysis to identify key influencers and streamline stakeholder engagement. The survey findings indicate that respondents expressed strong agreement (M=4.58, SD=1.23, and a 95% CI of [4.12, 5.04]) with the predictive analytics contributions of reduced negotiation time, improved compliance, and stronger relational governance. The paper offers practical implications for industries seeking agile and data-driven contracting solutions, supporting the emerging discourse on digital transformation in contract management.

Fields of Study & Subjects

Artificial Intelligence in Law Digital Transformation in Law Artificial Intelligence Applications

Publication details

Journal / source
International Conference on Artificial Intelligence and Social Network Systems (AISNS)
Pages
26–30
Publication date
9 January 2026
Language
EN