An Edit-centric Approach for Wikipedia Article Quality Assessment

TL;DR

This paper introduces an edit-centric model for Wikipedia article quality assessment that jointly estimates edit quality and generates descriptive explanations, offering a complementary approach to existing document-based methods.

Contribution

It presents a novel model combining classification and natural language generation to evaluate and explain Wikipedia edits, enhancing interpretability and efficiency.

Findings

Model effectively estimates edit quality

Generates natural language descriptions of edits

Proves feasible and cost-effective in empirical tests

Abstract

We propose an edit-centric approach to assess Wikipedia 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 cost-effectiveness in terms of data and quality requirements.