Enriching Wikipedia Vandalism Taxonomy via Subclass Discovery

Si-Chi Chin, W. Nick Street

Abstract: This paper adopts an unsupervised subclass discovery approach to automatically improve the taxonomy of Wikipedia vandalism. Wikipedia vandalism, defined as malicious editing intended to compromise the integrity of the content of articles, exhibits heterogeneous characteristics, making it hard to detect automatically. The categorization of vandalism provides insights on the detection of vandalism instances. Experimental results demonstrate the potential of using supervised and unsupervised learning to reproduce the manual annotation and enrich the predefined knowledge representation.