10.14456/jiskku.2023.29
Sentiment Analysis of New Normal Tourism Data in Chiang Mai Province After the COVID-19 Pandemic
รหัสดีโอไอ
10.14456/jiskku.2023.29
Creator Phichete Julrode
Title Sentiment Analysis of New Normal Tourism Data in Chiang Mai Province After the COVID-19 Pandemic
Contributor Warut Hansuwanpisit
Publisher Department of Information Science, Faculty of Humanities and Social Sciences, Khon Kaen University
Publication Year 2566
Journal Title Journal of Information Science Research and Practice
Journal Vol. 41
Journal No. 4
Page no. 76–92
Keyword Service user reviews, Sentiment analysis, Tourist Service, COVID-19
URL Website https://www.tci-thaijo.org/index.php/jiskku/index
Website title Journal of Information Science Research and Practice
ISSN 3027-6586
Abstract Purpose: The objectives of this research aim to conduct a comprehensive analysis of the sentiment analysis of tourists who use services in Chiang Mai province. The analysis will be conducted including three types: neutral, positive, and negative. The results of the analysis will be presented in the form of a data visualization.Methodology: The technique used in this research is Logistic Regression analysis. This involves breaking long texts into words (Word Tokenization) and then analyzing reviewing comments by comparing them with a text corpus from Wisesight Sentiment (https://pythainlp.github.io). The corpus contains 24,075 comments that have been collected in a dataset and classified with labels naming the sentiment of each comment. These labels are used to train the Logistic Regression model to identify sentiment in new data. The trained model was then tested and applied to the collected data to classify sentiment levels. This was done using a ไพทอน program to create a model for analyzing three types of sentiment statements: neutral, positive, and negative. Finally, the dataset of 1,900 comments collected from the website was taken to test with the model, and classified by sentiment, and shown as a data visualization.Findings: Researchers collected 1,900 reviews of tourist destinations and service providers in Chiang Mai from the websites TripAdvisor.com and Wongnai.com. They then used these reviews to test a sentiment analysis model. The model was able to identify three levels of sentiment: neutral, positive, and negative. The results of the analysis were presented in a data visualization format to help businesses improve their services in the future.Applications of this study: Development of a natural language processing (NLP) analysis model based on opinions and feedback from service users to analyze the advantages, disadvantages, areas for improvement, and opportunities to address challenges. With a large and growing amount of data, it is necessary to have a step-by-step process for analyzing the sentiment of reviews and comments using machine learning techniques.
คณะมนุษยศาสตร์และสังคมศาสตร์ มหาวิทยาลัยขอนแก่น

บรรณานุกรม

EndNote

APA

Chicago

MLA

ดิจิตอลไฟล์

Digital File
DOI Smart-Search
สวัสดีค่ะ ยินดีให้บริการสอบถาม และสืบค้นข้อมูลตัวระบุวัตถุดิจิทัล (ดีโอไอ) สำนักการวิจัยแห่งชาติ (วช.) ค่ะ