As businesses are having growth of data, there was a need to manage their data in a central relational database. Thus, Enterprise Resource Planning (ERP) systems were created running using such databases. ERP systems structure and store data that comes from many business transactions. Institutes selling ERP systems often use social media to promote their products and services, notify and educate clients about upcoming promotions, and keep in touch with their direct market from anywhere. It can also be a good source of information to monitor customer sentiments related to such software. In this work, a learning model from previous work (Soussan and Trovati, 2020a; Soussan and Trovati, 2020b) called Sentiment Urgency Emotion Detection (SUED) has been implemented on the Twitter account of an enterprise application software (EAS) institution which is SAP. This model is based on three classifiers which are sentiment analysis, urgency detection, and emotion classification. The model was previously trained to have a good accuracy and F1 score in order for it to be able to correctly categorize tweets regarding SAP products, check what sentiments and emotions can be detected regarding these products, and check how urgent the tweets are.