Constructing and Analyzing Different Density Graphs for Path Extrapolation in Wikipedia

TL;DR

This paper develops and analyzes graph-based models, especially an extended GRETEL with hypergraph features, to improve path extrapolation in Wikipedia navigation, highlighting the importance of connection quality over size.

Contribution

It introduces an enhanced GRETEL model with dual hypergraph transformation and combined features, demonstrating improved performance on dense Wikipedia graphs.

Findings

Hypergraph features improve model accuracy.

Dense graphs yield better predictions than sparse ones.

Connection quality impacts predictive success more than dataset size.

Abstract

Graph-based models have become pivotal in understanding and predicting navigational patterns within complex networks. Building on graph-based models, the paper advances path extrapolation methods to efficiently predict Wikipedia navigation paths. The Wikipedia Central Macedonia (WCM) dataset is sourced from Wikipedia, with a spotlight on the Central Macedonia region, Greece, to initiate path generation. To build WCM, a crawling process is used that simulates human navigation through Wikipedia. Experimentation shows that an extension of the graph neural network GRETEL, which resorts to dual hypergraph transformation, performs better on a dense graph of WCM than on a sparse graph of WCM. Moreover, combining hypergraph features with features extracted from graph edges has proven to enhance the model's effectiveness. A superior model's performance is reported on the WCM dense graph than on the larger Wikispeedia dataset, suggesting that size may not be as influential in predictive accuracy as the quality of connections and feature extraction. The paper fits the track Knowledge Discovery and Machine Learning of the 16th International Conference on Advances in Databases, Knowledge, and Data Applications.