Visualizing Statistical Linked Knowledge for Decision Support

Submitted by Adrian M.P. Bra... on 09/16/2015 - 01:39

Tracking #: 1168-2380

Authors: 
Adrian M.P. Brasoveanu
Marta Sabou
Arno Scharl
Alexander Hubmann-Haidvogel
Daniel Fischl

Responsible editor: 
Guest editors linked data visualization

Submission type: 
Full Paper
Abstract: 
In today’s interconnected world decisions often need to consider information from various domains. For example, a tourism manager needs to correlate tourist behavior with financial or environmental indicators to make long-term decisions about planning a tourism destination. Statistical data enables a broad range of such cross-domain decision tasks. A variety of statistical data sets are available and various visual analytics solutions are built to support decision making on these datasets. However, an open question refers to what are the principles, architecture, workflows and implementation design patterns that need to be followed for building such visual, cross-domain decision support systems. This article describes a methodology to integrate and visualiase cross-domain statistical data sources by applying selected RDF Data Cube (QB) principles. A visual dashboard built according to this methodology is also presented and evaluated in a tourism specific use case. The results show that a good quality interface was created by following the methodology and that this interface can improve decision making tasks for tourim managers.
Full PDF Version: 
PDF icon swj1168.pdf
Previous Version: 
Visualizing Statistical Linked Knowledge Sources for Decision Support
Tags: 
Reviewed

Decision/Status: 
Accept

Solicited Reviews:
Click to Expand/Collapse
Review #1
By Luc Girardin submitted on 07/Oct/2015
Suggestion:
Accept
Review Comment:

I am satisfied with the revisions and believe that the paper is ready for dissemination.

Review #2
By Bernhard Schandl submitted on 02/Nov/2015
Suggestion:
Accept
Review Comment:

The paper has been significantly extended (most notably with a qualitative evaluation), which adds a lot of strength to this paper. With these extensions all my previous concerns were addressed.

Review #3
By Emmanuel Pietriga submitted on 17/Nov/2015
Suggestion:
Accept
Review Comment:

This revision makes numerous and significant improvements to the original submission. Section 6.1 is particularly interesting. I am recommending acceptance, pending the following minor improvements:
- Many sections were not even spellchecked. The paper MUST be proofread. There are too many typos and grammatical errors, including the abstract.
- The language style in some paragraphs of Section 6.1 should be reworked. Many instances of "you" or "your" (pages 14-15) which sound weird in a research paper.
- In several places acronyms (such as DMO) are not explained, or explained later. This should be fixed.
- Some references miss important information, such as publication venue...
- Several instances of (see Section), missing the actual section number.
- Page 23: provide information about where to find the data and visualization services, which were supposed to be released in October 2015.