The Purpose of This Paper Is Verify the Efficiency of Sentiment Analysis and Comparative Analysis, While the Prevalence of Social Networking, More and More Research Is Being Done In the Area of Tweet Analysis. Twitter Use As the Media For Sharing Information By Many People, Twitter Become a Valuable Topic For Further Discussion When the Wave of Using Twitter As a Communication Tool Makes Sentiment Analysis. In This Research We Attempt to Present the Data Mining Based Sentiment Analysis Tool, It Tries to Compare Three Functions Finding Positive, Negative Tweets, Neutral Tweets from Information Resources and Sentiment Analysis Among Twitter Tweets. Here We Also Do Preprocessing So It Helps to Improve Performance. Then We Use Machine Learning Algorithm. This Model Concentrate on Examine Tweets from Those Media Sites, Thus Provide a Way to Find Out Technology Trends In the Future.