Customer Satisfaction Toward Commercial E-Services in Saudi Arabia: A Sentiment Analysis

The e-government in Saudi Arabia has evolved significantly over the last two decades. Therefore, this study investigated the commercial e-services provided by the Saudi Ministry of Commerce (MOC). Sentiment analysis was conducted to assess customer satisfaction using these MOC's e-services. To this end, data were collected from Twitter and App reviews, after which two approaches were applied to the analysis: manual annotation- and lexicon-based approaches. Then, each experiment was evaluated using three machine learning classifiers, namely, support vector machine (SVM), Naïve Bayes (NB), and logistic regression (LR), based on several metrics such as accuracy, precision, recall, and the F1-score. The results showed that more than 90% of the data was neutral, and that more users were negatively satisfied with the MOC's e-services than were satisfied with them. Furthermore, based on the accuracy of all three classifiers, the results indicated that while the manual annotation approach outperformed the lexicon-based approach, SVM showed better performance than NB and LR in the two experiments.