SA places reviews

Sentiment analysis is a rapidly evolving technique to verify the emotional tone, especially for text analysis reviews. Studies on Arabic sentiment analysis are sparse, particularly about the Saudi tourist industry. This research aims to improve the standard of tourism and tourist experiences in Saudi Arabia and help achieve the Saudi Vision 2030 goals. One of these goals is to stimulate economic growth by improving tourism-related commerce, as Saudi Arabia is increasingly becoming a tourist destination for foreign travelers. This paper employs sentiment analysis of tourist experiences in places recognized as popular attractions by the Saudi Tourist Ministry. Arabic-language tourist reviews of Boulevard Riyadh City, Al-Ula Old Town, the Al-Balad district in Jeddah, the Heritage Village in Dammam, and the Al-Hada cable car from Google Maps are collected, and the sentiment of the reviews is classified as positive, negative, or neutral. Textual representation techniques used in the model word embedding are AraVec, Arbert, Qarib, and Marbert. Moreover, different baseline models, such as Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), Decision Tree (DT), and deep learning models such as Bidirectional Long Short-Term Memory (BLSTM), Recurrent Neural Network (RNN), and Convolutional Neural Network (CNN) as transformer-based classification (Arabert, Arbert, Marbert, and Qarib), were implemented to predict sentiment. Various optimizations, such as accuracy, precision, recall, F1 score, and the Accuracy Under Constrained (AUC), evaluate the models\u2019 performance. The results demonstrate that Qarib achieves the promised super performance in all data situations. Meanwhile, the Convolutional Neural Network model performs better using classic and contextual embeddings.