Home // DATA ANALYTICS 2021, The Tenth International Conference on Data Analytics // View article
Authors:
Alexandros Bousdekis
Dimitris Kardaras
Stavroula Barbounaki
Keywords: sentiment analysis; probabilistic model; machine learning; data analytics; hotel review; tourism management; opinion mining.
Abstract:
Customers have access to different sources of information, and generate their own content and share their views and experiences which are expressed through online review comments and ratings about products and services. However, the increasing amount of data has reached a level that makes manual processing impossible, requiring data-driven approaches. Sentiment analysis is rapidly emerging as an automated process of examining semantic relationships and meaning in reviews. Despite the large amount of research works dealing with sentiment analysis, the consistency between the customer opinions expressed in review comments and the rating that they provide has not been explored. In this paper, we propose an approach incorporating the Valence Aware Dictionary for Sentiment Reasoning (VADER) algorithm for extracting the polarity of the review comments and Bayesian Networks for revealing the relationships between the aforementioned sentiment scores and the online rating. The proposed approach was validated in the tourism domain using a dataset with hotel reviews, extracted from the TripAdvisor.
Pages: 92 to 97
Copyright: Copyright (c) IARIA, 2021
Publication date: October 3, 2021
Published in: conference
ISSN: 2308-4464
ISBN: 978-1-61208-891-4
Location: Barcelona, Spain
Dates: from October 3, 2021 to October 7, 2021