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.

Rapid Production Method of Massive Thematic Maps Based on Geospatial Knowledge Extraction

“…Since the data stock of research literature is large and constantly updated in real time, the clustering method uses the leaderfollower incremental clustering strategy [32] . The specific process is as follows: in the clustering process, the set of centers C of existing clusters is kept, C={c1,c2...cn}, where c denotes the cluster center obtained by combining the keywords contained in its class clusters, and when a new keyword Ii is clustered, the spatial, temporal, and semantic similarity measures are used to calculate the spatial and temporal similarity between the new keyword Ii and the center c of each class cluster [33] . If the spatio-temporal semantic similarity between the new information item Ii and the existing class cluster c, Total_sim(Ii,c) is greater than a certain threshold (0.7 in the study), then Ii is included in the class cluster c. The calculation formula is as in formula6.…”

Fine-tuned Predictive Model for Verifying POI Data

“…Geotagging is the important activity to generate POI data and many researchers worked in this domain [36][37][38][39]. Some authors suggested the techniques to inference the geographical location based on text, image and categories [40][41][42][43][44][45][46][47]. Authors explained that even incomplete data can also be useful hence we divided the dataset into four classes and proposed a method to categorize the POI in a suitable class [48].…”

Antimicrobial Resistance Risk Assessment Models and Database System for Animal-Derived Pathogens

“…The B/S system framework does not require the installation of traditional software, and most of the work is conducted by the server [ 41 , 42 ]. The costs to users and the workloads of system maintenance and management are directly reduced, which results in improved independence, adaptability, scalability, and security [ 43 , 44 ].…”