Tools
Tools
Kierans, Niall (2024) Sentiment Analysis of Airport Google Reviews: A Comparative Study of Natural Language Processing Techniques and Machine Learning Models. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (2MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (3MB) | Preview |
Abstract
Airports play a central role in the global travel network, and their efficiency and service quality significantly impact passenger satisfaction. In this study, we explore the potential of Natural Language Processing (NLP) and Machine Learning (ML) techniques to analyse customer sentiments reflected in Google reviews of various airports. A sample of airport reviews was collected from Google, and NLP techniques like tokenisation, stop-word removal, and lemmatisation were applied to prepare the data. Sentiment classification was performed using dictionary-based lexicons (Vader, NRCLex, TextBlob) and then with ML models (SVM, Random Forest, Na¨ıve Bayes). Finally, NLP and ML models were blended for further experimentation.
The analysis revealed key insights into the aspects of airport services that influence passenger sentiment, such as cleanliness, staff behaviour, waiting times, and facilities. The results indicate that the blending of NLP with ML models provides a strong framework for sentiment analysis, offering reliable predictions and valuable insights. The insights gained can guide airport management in making informed decisions to elevate service quality and boost passenger satisfaction.
Actions (login required)
 |
View Item |