Visualization of Location-Referenced Web Textual Information Based on Map Mashups

Abstract

Space is the most fundamental organizing dimension for information that forms the basic spatial understanding around which all other temporal and semantic details are situated. Various types of web information are present in our daily lives, and spatial content can facilitate the understanding of that information. Hence, many studies have been conducted to extract the implicit spatial location from different web resources, and they have mainly investigated web textual information. However, the existing studies mainly focus on the extraction or simple presentation of the location of the information, while further exploration and visualization of the information through the comprehensive consideration of its spatial, temporal, and semantic dimensions have rarely been performed. Thus, this paper proposes a novel modeling and visualization framework for location-referenced web textual information. The framework applies an information model to structurally extract and resolve spatial content along with the temporal and semantic elements from the location-referenced information items. Based on the constructed information model, the information items are hierarchically clustered and visualized by combining map mashups with cartographic processes and methods. This framework enables users to interactively index and browses individual information items. Furthermore, the association relationships involved in the information set are explored in our work. With knowledge graphs that are automatically generated based on the information model, a high-level understanding of the information set can be obtained by users.