University of Konstanz
Graduiertenkolleg / PhD Program
Computer and Information Science

Christian Rohrdantz

Research Student in the PhD program from 16.04.2007 to 30.08.2008.


Prof. Dr. Daniel A. Keim

organisational data

E-mail: rohrdant "at"
Other Resources: Christian Rohrdantz Member Page

project description

Visual Analytics in high-dimensional Data Spaces

The rapidly increasing amount of data stored in today's databases environments requires efficient and effective methods to make the full use out of the collected data, i.e. to extract interesting and potentially useful patterns. But because of the dimensionality and volume of today's data sets, extracting the valuable information hidden in the data is a difficult task. New methods are needed to allow the analyst to examine these massive, multi-dimensional information sources to make effective decisions.

The aim of this research project is to develop Visual Analytics methods to detect and visualize potentially useful patterns in such high-dim. data spaces. Since a direct visualization of highdimensional data is difficult due to the limited number of visual variables (8 according to Bertin) and the difficulty in comprehending more than three dimensions to discover relationships, outliers, and clusters, the goal is to identify low dimensional projections of the data that reveal patterns in the original data space. The goal of the project is therefore to combine a) analytical techniques for detecting relevant patterns with b) low dimensional presentations to provide effective views.


The following list of publications covers only those, which are or were published during participation at the Graduiertenkolleg / PhD program.

Articles in Journals

  • Kisilevich, S., Rohrdantz, C., Veronica, M., Keim, D., What do you think about this photo? A novel approach to opinion and sentiment analysis of photo comments, International Journal of Data Mining, Modelling and Management (IJDMMM), 2011, Inderscience.

Conference Papers


Master Theses

  • Rohrdantz, C., Analyse größer Dokumentensammlungen: Charakterisierung von Themen und Identifizierung von Thementrends, University of Konstanz, September 2008.