Share these talks and lectures with your colleagues
Invite colleaguesPractice paper
Leveraging sentiment analysis as a predictor of risk in community engagement
Journal of Airport Management,
17
(2),
182-196
(2023)
Abstract
This study proposes a methodology based on sentiment analysis to compute an ‘engagement risk priority number’ or ERPN. The ERPN is a calculation designed to help airport management rank risks in community engagement and identify outreach strategies to airport stakeholders. The ERPN is based on three components of sentiment analysis (polarity, surprise, and subjectivity of residents' sentiments and opinions) that may predict potential risks to programme implementation and airport development. The methodology leverages the latest developments in natural language processing, specifically transformers, and compares the outcomes of these newer models with those of more traditional lexicon-based algorithms.
Keywords: airport community engagement; natural language processing; sentiment analysis; risk assessment
The full article is available to subscribers to the journal.
Author's Biography
Tony Diana is the division manager for outreach in the Office of NextGen at the US Federal Aviation Administration. His main interests are machine learning, natural language processing, performance evaluation and benchmarking. He is a member of the Aviation Economics and Forecasting subcommittee at the Transportation Research Board of the National Academies of Sciences, Engineering and Medicine. He is a Certified Lean Sigma Master Black Belt and a project management professional. He is a Lecturer in machine learning and natural language processing at the University of Maryland Baltimore County.
