Mining Online User-Generated Content: Investigating Travel Experiences in Manuel Antonio National Park

Authors: Luyu Wang*, University of Florida, Angélica Almeyda Zambrano, University of Florida, Zhaohe Xu, Amazon.com, Inc
Topics: Tourism Geography
Keywords: user-generated content, sentiment analysis, LDA, Manuel Antonio National Park
Session Type: Paper
Day: 4/6/2019
Start / End Time: 1:10 PM / 2:50 PM
Room: Congressional A, Omni, West
Presentation File: No File Uploaded


Social media plays an increasingly important role as an information source for travelers. Travelers can share traveling information and experiences through online textual data. The online textual data as a type of user-generated content (UGC) can convey feelings, sentiments, and opinions of tourists. TripAdvisor serves as the most prominent online third-party travel intermediary becoming a rich data source for data mining. Using online review data retrieved from TripAdvisor, the goal of this study is to investigate tourists’ experiences in Manuel Antonio National Park. Though the smallest of any Costa Rican national park, it weighs in as one of the most popular. This study focuses on not only quantitative ratings but also the meaning of the valuable reviews generated by tourists. In this study, sentiment analysis is employed to determine visitors’ emotions. It also adopted the Latent Dirichlet Allocation (LDA) analysis to explore the key topics of visitors’ reviews. We collected a large corpus of English and Spanish reviews to explore and unveil how different the rated experiences are. Also, travel experiences of different types of reviewers such as family traveler, couple traveler, solo traveler are identified to understand their travel preferences. This study aims to provide feasible suggestions to improve park management and tourist's experience.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login