Model-based Sentiment Analysis of Customer Satisfaction for the Jordanian Telecommunication Companies

Nowadays, social networks are considered to be the most useful data source for analysis trend. The data can be used for different goals, for instance, the commercial companies use the Facebook pages to discover their customer satisfaction of the provided services. This research targets sentiment analysis the customers' posts on the formal Facebook pages of the Jordanian telecommunication companies. The dataset of this paper is collected from three main Jordanian telecommunication companies: Orange, Zain, and Umniah. A supervised based approach including K Nearest Neighbors, Support Vector Machine, Naive Bayes, and Decision Trees are applied and a comparison between them is provided in term of accuracy metrics. In this study, we introduce a model that is able to make a sentiment analysis of the customer posts on Facebook written in Jordanian dialect.