How Large Language Models Empower the Analysis of Online Public Engagement for Mega Infrastructure Projects: Cases in Hong Kong

Abstract

Mega infrastructure projects (MIPs) have profound societal impacts, and public engagement plays a crucial role in their success. The rise of social media enables the dynamic analysis of public opinions, aiding decision-makers in addressing public concerns. This study introduces a networking, parsing, retrieval, and mapping approach that innovatively leverages large language models (LLMs) for massive text parsing and social network analysis. Using data from Hong Kong's nine MIP topics, this study identifies influencers and examines public and influencer engagement across project lifecycles. The findings and constructed managerial maps reveal the hidden dynamics of involvement and interaction across different project event types, enabling a prioritized management method. The novel LLM-driven framework offers decision-makers actionable insights to comprehensively optimize online public communication and engagement strategies for MIPs.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 9 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.