The anti-social behaviours in online social media follow some documented psychological trends. Informal texts used to perpetrate the anti-social act contain information of the psychological trends. That information can be useful in the task of identifying an offensive text in the social media. In this regard, we used psychometric information as a feature-set in conventional classifiers for the classification task of informal texts used in online social-media. In this paper, we investigated whether this has any positive effect on the performance of those classifiers. The results of our experiments show some promising outcomes. It appears that the psychometric information enriched the data set, which improved the performance of some classifiers in the classification of online informal text.