Topic Modelling of Online Reviews for Airports

Elizabeth John, Dona (2023) Topic Modelling of Online Reviews for Airports. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

This study used topic modeling approaches to successfully categorize travelers’ reviews of major airports around the world by department. The goal was to distribute these categories to appropriate department managers in order to gain a better knowledge of the traveler experience and suggest areas for improvement within airport departments. The existing research highlights the significance of understanding the traveler experience and how airports influence it. Prior to this effort, however, there has been no study focused on reviewing traveler opinions to determine specific areas for improvement in various airport departments. This work bridges that gap by employing topic modeling, particularly by utilizing qualitative and quantitative methodologies such as statistical data analysis and topic modeling techniques such as Latent Dirichlet Allocation (LDA), CountVectorization, and TF-IDF. Topic modeling was used to discover major themes significant to different airport departments in accordance with traveler reviews. The identified topics were: ”Parking desk”, ”Travel desk” and ”Outlet desk”. The coherence score resulted for the LDA model using CountVectorization was 0.553. The study gained important insights into particular areas for development throughout various airport divisions by taking this method. These information are expected to help airport management handle traveler problems and improve the overall experience for travelers. The study’s findings not only help to improve services and raise airport standards, but they also establish the groundwork for developing a comprehensive system for airport administration to efficiently solve traveler difficulties. Airport management can proactively improve their services and prioritize areas that demand attention by taking into account the identified concerns and employing the results of topic modeling.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Mulwa, Catherine UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Aviation Industry H Social Sciences > HF Commerce > Customer Service
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	22 Nov 2024 11:08
Last Modified:	22 Nov 2024 11:08
URI:	https://norma.ncirl.ie/id/eprint/7186

Actions (login required)

View Item