Sentiment analysis is a hot topic today. The purpose of this research is finding out sentimental state of a person or a group of people using data mining. The target of this research is building a user friendly interface for general people, so that they will be able to see the analysis report very easily. This analysis process contains both supervised and unsupervised learning, which is a hybrid process. Analysis is done based on keywords, which is defined by the user. User is able to set the number of tweets he/she wants to analyze. We used web-based library for the system. The system is tested and found satisfactory result.