DARE: Distance and angle retrieval environment: A tale of the two measures

Abstract

This article presents a visualization tool for information retrieval. Some retrieval evaluation models are interpreted in the two‐dimensional space comprising direction and distance. The two different similarity measures—angle and distance—are displayed in the visual space. A new retrieval means based on the visual retrieval tool, the controlling bar, is developed for a search.

The influence of indexing practices and weighting algorithms on document spaces

“…Descriptors were used instead of keywords because the former provides a more accurate subject description of document content. Although the dataset is small compared to today's gigabyte data sources, the investigators wished to keep the dataset size manageable for processing purposes using an IR environment, the Distance Angle Retrieval Environment (DARE; discussed later), developed by Zhang and Korfhage (1999).…”

“…The generated documents based on the descriptor frequency and exhaustivity distributions were projected onto the DARE (Zhang, 2000;Zhang & Korfhage, 1999) visual IR environment. DARE is a two-dimensional visual retrieval tool, consisting of a graphical representation of the visual distance and the visual angle as the x axis and y axis, respectively.…”

A Pairwise Distances Based Visualization System for Information Retrieval

“…In most current visualization system such as DARE (Zhang and Korfhage, 1999;Zhang, 2000), TOFIR (Zhang, 2001), and GUIDO (Korfhage, 1991), object distribution algorithm employing global reference point(s), decide the position of each document in the visual space. Different from currently system, our system choose reference points dynamically according to pairwise distances among documents.…”

“…For example, DARE [1], TOFIR [2] and GUIDO [3] are designed based on Euclidean distance and/or angle to visualize each document's relevance, referring to some predefined reference points. [4], [5] and [6] provide another approach by mapping the value of each dimension in the high-dimensional vector space, into a dense colored pixel of the visual space.…”

Visualization for Information Retrieval

“…Motivated by this connection, researchers employed the two distinctive spatial characteristics of distance and angle, and their combination to establish several information retrieval visualization models such as DARE (Zhang and Korfhage, 1999;Zhang, 2000), TOFIR , and GUIDO (Korfhage, 1991;Nuchprayoon and Korfhage, 1994;Nuchprayoon and Korfhage, 1997). Motivated by this connection, researchers employed the two distinctive spatial characteristics of distance and angle, and their combination to establish several information retrieval visualization models such as DARE (Zhang and Korfhage, 1999;Zhang, 2000), TOFIR , and GUIDO (Korfhage, 1991;Nuchprayoon and Korfhage, 1994;Nuchprayoon and Korfhage, 1997).…”