Fast Mining of Spatial Frequent Wordset from Social Database

TL;DR

This paper introduces a fast algorithm for mining spatial frequent wordsets from social data, utilizing a novel data model and an SFP-tree structure to efficiently identify location-specific patterns.

Contribution

It presents a new spatial social data model and an SFP-tree based algorithm for efficient mining of spatial frequent patterns from social datasets.

Findings

Efficient extraction of spatial frequent patterns demonstrated.

Introduction of SFP-tree structure for pattern mining.

Algorithm outperforms existing methods in speed and accuracy.

Abstract

In this paper, we propose an algorithm that extracts spatial frequent patterns to explain the relative characteristics of a specific location from the available social data. This paper proposes a spatial social data model which includes spatial social data, spatial support, spatial frequent patterns, spatial partition, and spatial clustering; these concepts are used for describing the exploration algorithm of spatial frequent patterns. With these defined concepts as the foundation, an SFP-tree structure that maintains not only the frequent words but also the frequent cells was proposed, and an SFP-growth algorithm that explores the frequent patterns on the basis of this SFP-tree was proposed.