An edit-centric approach forwikipedia article quality assessment

Abstract

We propose an edit-centric approach to assessWikipedia article quality as a complementary alternative to current full document-based techniques. Our model consists of a main classifier equipped with an auxiliary generative module which, for a given edit, jointly provides an estimation of its quality and generates a description in natural language. We performed an empirical study to assess the feasibility of the proposed model and its costeffectiveness in terms of data and quality requirements.