Simulation, Modelling and Classification of Wiki Contributors: Spotting The Good, The Bad, and The Ugly

TL;DR

The paper tackles the reliability challenges of crowdsourced wiki data by proposing a real-time profiling and classification pipeline for Wikivoyage contributors. It combines data stream processing, synthetic data generation to balance imbalanced classes, incremental profile updates, and a two-level stacking classifier to simultaneously detect human vs. bot and benevolent vs. malignant contributions. Empirical results on a Wikivoyage dataset show high performance, with binary and multi-class setups achieving up to around 92% accuracy and strong F-measures, validating the practical viability of online monitoring for vandalism and manipulation. This approach enables proactive quality control of wiki content and has broad implications for improving data integrity in crowd-sourced knowledge platforms.

Abstract

Data crowdsourcing is a data acquisition process where groups of voluntary contributors feed platforms with highly relevant data ranging from news, comments, and media to knowledge and classifications. It typically processes user-generated data streams to provide and refine popular services such as wikis, collaborative maps, e-commerce sites, and social networks. Nevertheless, this modus operandi raises severe concerns regarding ill-intentioned data manipulation in adversarial environments. This paper presents a simulation, modelling, and classification approach to automatically identify human and non-human (bots) as well as benign and malign contributors by using data fabrication to balance classes within experimental data sets, data stream modelling to build and update contributor profiles and, finally, autonomic data stream classification. By employing WikiVoyage - a free worldwide wiki travel guide open to contribution from the general public - as a testbed, our approach proves to significantly boost the confidence and quality of the classifier by using a class-balanced data stream, comprising both real and synthetic data. Our empirical results show that the proposed method distinguishes between benign and malign bots as well as human contributors with a classification accuracy of up to 92 %.

Figures (4)

• Figure 1: Proposed stream-based classification of wiki contributors.
• Figure 2: Distribution of the data set in terms of user type and contribution type targets.
• Figure 3: K-means optimal K value based on mean distance deviation.
• Figure 4: Proposed data stream multi-class stacked classification of contributors.