(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 13, No. 6, 2022 Tourist Reviews Sentiment Classification using Deep Learning Techniques: A Case Study in Saudi Arabia Banan A.Alharbi, Mohammad A. Mezher, Abdullah M. Barakeh Dept. of Computer Science, Fahad Bin Sultan University, Tabuk, Saudi Arabia Abstract—Now-a-days, social media sites and travel blogs have become one of the most vital expression sources. Tourists express everything related to their experiences, reviews, and opinions about the place they visited. Moreover, the sentiment classification of tourist reviews on social media sites plays an increasingly important role in tourism growth and development. Accordingly, these reviews are valuable for both new tourists and officials to understand their needs and improve their services based on the assessment of tourists. The tourism industry anywhere also relies heavily on the opinions of former tourists. However, most tourists write their reviews in their local dialect, making sentiment classification more difficult because there are no specific rules to control the writing system. Moreover, there is a gap between Modern Standard Arabic (MSA) and local dialects. one of the most prominent issues in sentiment analysis is that the local dialect lexicon has not seen significant development. Although a few lexicons are available to the public, they are sparse and small. Thus, this paper aims to build a model capable of accurate sentiment classification in the Saudi dialect for Arabic in tourist place reviews using deep learning techniques. Machine learning techniques help classifying these reviews into (positive, negative, and neutral). In this paper, three machine learning algorithms were used, Support -Vector Machine (SVM), Long short-term memory (LSTM), and Recurrent Neural Network (RNN). These algorithms are classified using Google Map data set for tourist places in Saudi Arabia. Performance classification of these algorithms is done using various performance measures such as accuracy, precision, recall and F- score. The results show that the SVM algorithm outperforms the deep learning techniques. The result of SVM was 98%, outperforming the LSTM, and RNN had the same performance of 96%. Keywords—Sentiment classification; Saudi dialect; support - vector machine; recurrent neural network; long short-term memory I. INTRODUCTION Due to the astounding and quick expansion of social networking sites, an increasing number of individuals are sharing their experiences and opinions on various issues, including travel, hotels, physical items, movie reviews, and health. One cannot deny that social media sites play a role in people's daily and social lives. Additionally, they assist tourists in selecting the appropriate destination via their comments on tourist destinations' social media sites, as mentioned by [1]. Moreover, social media sites have gained a significant attraction on the web. These sites have evolved into an indispensable resource for travelers whose decisions are influenced by the reviews and opinions of other travelers. Human emotions and emotional cognition influence purchasing decisions, travel, and other variables. Online reviews can help researchers and business owners understand tourists' needs and preferences correctly. It was further noted that the tourism industry's primary reliance on the opinions and perceptions of former travelers is universal. They emphasized that [2] the views expressed by tourists in the comments play a role in influencing the choices of other tourists for their travel destinations. Moreover, travelers frequently desire to know the attractions for which a city they wish to visit is renowned. They research social media sites for recommendations, opinions, and reviews to visit tourist destinations. Given the plethora of information and evaluations, it is difficult for travelers to obtain reliable judgments and select the best hotels, restaurants, and attractions. Many people share their experiences and views spontaneously and more credibly about the tourist places they visit without a financial return. Therefore, it will be challenging for the reader to locate relevant websites when researching, rewriting, and summarizing the facts and viewpoints vital to them. Consequently, the significance of sentiment classification reduces the time and effort required to extract relevant information for travellers. The sentiment classification process studies people's emotional state and their assessments of a particular topic or their attitudes towards a specific event, and sentiment classification is used in tourism applications, products, shopping and other areas of life. Consumers place greater credence on online reviews, personal recommendations, and comments and thus are more likely to provide product reviews after purchasing. The classification process aims to determine the polarity of the text and determine whether a person feels optimistic about a particular product, negative or neutral. Classifying reviews (positive or negative) is the goal of sentiment classification, and like the use of text, analysis has proven cost-effective. The classification is mainly based on an explained supervised learning approach [3]. As a result, sentiment classification is one of the most active and prosperous research areas in Natural Language Processing (NLP). Many researchers and those interested in this field use deep learning for sentiment classification. Data technologies reduce sentiment classification errors to ensure the highest accuracy on social media [4]. This study aims to develop a model capable of accurate sentiment classification in the Saudi dialect of Arabic by analyzing tourist location reviews using deep learning techniques. 717 | Page www.ijacsa.thesai.org