ABSTRACT The fame of Twitter in Tamilnadu tempts spammers. Spammers send unwanted tweets to Twitter users to promote websites, services, or products, which are unsafe to normal users. Earlier researchers presented many contrivances to stop these benevolent of activities. Accordingly, topical approach as well as the twitter work on spam detection by applying machine learning skills into Twitter to detect spam tweets. Lack of studies on which researcher focus on the spam detection in twitter within the Tamilnadu community. There is a large number of spams reply on twitter especially on the trending twitter account. In this paper, we bridged the gap by classifying the spam tweets by using ML approach. Collected a large dataset of Twitter that includes 2,903 tweets approximately. Using tweets related trending topics. Construct a large labeled collection of users. Then, we classify tweets manually into spams and non-spams. The results show the streaming spam tweet detection is still a big challenge and a robust detection technique should take into account.