Using Sentiment Analysis of Arabic Tweets to Fine-Tune CRM Structure

Abstract

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.