DBSCAN

A density-based clustering algorithm introduced by Ester, Kriegel, Sander, and Xu (1996) that groups data points located in dense neighbourhoods and labels sparse points as noise. Unlike k-means, DBSCAN does not require the user to specify the number of clusters in advance and can find non-convex cluster shapes. Two parameters control its behaviour: ε (the neighbourhood radius) and min_samples (the minimum density to form a core point). In web accessibility research, DBSCAN is used (often alongside t-SNE for dimensionality reduction) to cluster web pages by structural similarity, supporting representative sampling methodologies such as OPTIMAL-EM.