Easy access to the internet throughout the world has fully reformed the usage of social communication such as Facebook, Twitter, Linked In which are becoming a part of our life. Accordingly, cybercrime has become a vital problem, especially in developing countries. The dissemination of information with no risk of being discovered and fetched leads to an increase in cyber-criminal. Meanwhile, the huge amount of data continuously produced from Twitter made the discovery process of cyber-criminals is a tough assignment. This research will contribute in determined on the build the comparable vectors for (positive and negative classes) and then the classify incoming tweets to predicate his class (positive or negative). The proposed routines staring with the construct super comparable vectors (SCV) (positive and negative vectors), and the construct vector for the incoming tweet, and then calculate similarities with both SCV and compare calculated similarities to predicate class of incoming tweet. In this research, we used some common techniques for calculating the weight of terms in tweets to construct SCV. To ensure the successful operation of the proposed system, we performed a pilot analysis on a real example of an examination. Research Improves precision, recall, and F1 values by 87%, 59%, 69.99%, respectively.