Tracking the effect of change a telecom service on customer feeling is an important process for telecom companies. As a result of tangible growth and large competition among telecom companies, customer retention and satisfaction are the most important challenges faced by telecom companies nowadays. Customer retention can be achieved by identifying the feeling of the telecom customers after changing service and take care of the customers by modifying the services that aren't accepted by its customers. Hence, this article was done by using a combination of four stages of: text pre-processing, personality analysis, sentiment analysis, and a chatbot system. This article shows the effect of using the personality traits, agreeableness and emotional range, with sentiment analysis to help reaching a full description of customer feel. Combining the sentiment analysis Naïve Bayes technique in the natural language processing and personality insights pre-learning stage and adding feedback using the obtained results achieves higher accuracy than using the traditional sentiment analysis techniques.