Tagging is a machine learning technique that provides tags to the information that the user can easily identify the related information. Manual tagging is widely used for constructing question banks; but, this approach is time-consuming and it would create pathway to consistency issues. Semi-manual tagging which is time-consuming and people must be experts in that domain have the ability to identify the question and tag them it is not possible in real-time and high in cost. The proposed associate degree automatic tagging exploitation information processing that mechanically tags automatic question tagging. In this paper, step up with a keywords-based model to automatically tag questions with information units. With regard to multiple-choice questions, the proposed models use mechanisms to capture helpful information from keywords to boost tagging performance. Automatic tagging method using NLP automatically tag questions where users can get information regarding to his search which overcomes earlier methods. In our experiments, the result shows that the model is credible and outperforms various existing models.