Virtual Booth

              Tourism in Thailand's three southern border provinces—Yala, Pattani, and Narathiwat—has drawn increasing attention from the government and private sectors due to the region's natural beauty and distinctive cultural heritage. Recognized as a key driver of economic growth and a source of income for local communities, tourism in these provinces requires a deeper understanding of public perceptions to enhance promotion and planning efforts. Sentiment analysis is built from the information provided through text (reviews) to help understand the social sentiment toward their brand, product, or service. Therefore, this study leverages social media data sentiment analysis to investigate tourists' opinions and attitudes toward visiting these areas.

              The study constructs a sentiment analysis model by integrating text and reviews related to tourism from websites and social media platforms in the English language. The data undergoes preprocessing steps, including noise removal, word tokenization, and stopword elimination, and subsequently feature engineering methods for analysis. The word clouds were generated to visualize the dominant words; thus, stakeholders can pinpoint what aspects of a service, product, or location are being frequently discussed, allowing for targeted improvements or promotions. Machine learning algorithms, including Logistic Regression (LR), Naïve Bayes (NB), Random Forest (RF), and Artificial Neural Network (ANN) are used to build the sentiment analysis model. The sentiment model's performance indicates that the proposed model is suitable for sentiment prediction, attaining an accuracy of 0.87, precision of 0.90, recall of 0.94, and an F1 score of 0.92 for the ANN model. The findings are visualized through an interactive dashboard and used to predict the sentiment of a new review, providing actionable insights into public sentiment toward tourism in the southern border provinces.