PurposeThe purpose of this paper is to propose a structured multilevel system that will distinguish the anomalies present in different online social networks (OSN).Design/methodology/approachAuthor first reviewed the related work, and then, the research model designed was explained. Furthermore, the details regarding Levels 1 and 2 were narrated.FindingsBy using the proposed technique, FScore obtained for Twitter and Facebook data set was 96.22 and 94.63, respectively.Research limitations/implications Four data sets were used for the experiment and the acquired outcomes demonstrate enhancement over the current existing frameworks.Originality/valueThis paper designed a multilevel framework that can be used to detect the anomalies present in the OSN.