Hamed Al-Rubaiee

Understanding how customers perceive the services they receive has always been crucial to a business’s success. It is widely accepted that Customer Relationship Management (CRM) and Customer Experience Management (CEM) have both been shown to aid businesses in making better decisions by providing them with better information. Unfortunately, in real-world business applications, there are distinctions between customer opinions collected through customer relationship management (CRM) and the real customer opinions gathered via social media for customer experience management (CEM). It is critical to close this gap between the two to match customer expectations. Both CRM and CEM have been recognised as tools that can help firms make better decisions. However, until recently, the problem of integrating unstructured data from CEM directly into CRM was largely ignored, and, particularly in the Arabic language, it has remained unsolved. Thus, the goal of this study is to offer a framework for CRM modification via CEM that integrates a semantic orientation method and supervised machine learning. Sentiment analysis was utilised to enhance the CRM structure to add important aspects that were missing. The results of this study show that businesses could undoubtedly make more informed decisions by expanding their CRM structure to incorporate more of the issues discussed by customers on social media. Surprisingly, the negative class had the most label matching between CRM and CEM.

In this study, we present the design and implementation of Arabic text classification in regard to university students' opinions through different algorithms such as Support Vector Machine (SVM) and Naive Bayes (NB). The aim of the study is to develop a framework to analyse Twitter "tweets" as having negative, positive or neutral sentiments in education or, in other words, to illustrate the relationship between the sentiments conveyed in Arabic tweets and the students' learning experiences at universities. Two experiments were carried out, one using negative and positive classes only and the other one with a neutral class. The results show that in Arabic, a sentiments SVM with an n-gram feature achieved higher accuracy than NB both with using negative and positive classes only and with the neutral class.