in2vis - Interactive Information Visualization: Exploring and Supporting Human Reasoning Processes

Submitted by wolfgang on Sat, 11/17/2012 - 18:08
Aim

Our aims are

  • to explore and to compare different methods (Information Visualization, Exploratory Data Analys and Machine Learning) to ease the understanding (the human reasoning process), to find their strengths and limitations and to estimate how combinations of these methods can contribute to more in-depth reasoning processes; and
  • to develop guidelines how to explore and visualize data and information task- and user- appropriately.
Team
Project Partners
  • Insitute of Software Technology & Interactive Systems, Vienna University of Technology
  • Institute of Design and Assessment of Technology, Vienna University of Technology
  • Department of Child and Adolescent Neuropsychiatry, Medical University Vienna
Funding

This work is funded by the Vienna Science and Technology Fund (WienerWissenschafts-, Forschungs- und Technologiefonds - WWTF), grant WWTF CI038.

Contact
Status
finished

Users are confronted with a huge amount of abstract, but highly structured data. They want to accomplish different kinds of tasks, where they need different interactions and navigations as well as different views of the same data to gain more insight into the data under investigation.  These processes of investigation are very complex and only little guidance exists. Therfore our aims are

  • to explore and to compare different methods (Information Visualization, Exploratory Data Analys and Machine Learning) to ease the understanding (the human reasoning process), to find their strengths and limitations and to estimate how combinations of these methods can contribute to more in-depth reasoning processes; and
  • to develop guidelines how to explore and visualize data and information task- and user- appropriately.

To fullfill these aims we will conduct a study with medical data from Department of Child and Adolescent Neuropsychiatry at the Medical University of Vienna. This highly structured, time based, categorical data comes from questionnaires of girls with eating disorders (anorexia nervosa).

A new exploratory information visualization named Gravi++ was developed in the course of the in2vis project as the information visualization method of the study. This method was designed for our medical data and is able to help the user analyse the data and predict further development of the patients. It integrates a spring-based core visualization to display the multidimensional data set. To cope with the temporal dimension, we integrated animation and an additional view called Traces that maps the animation on a single image. Furthermore, the Star Plot view, Attraction Rings view, and the tooltips can give information on the exact values of each dimension. In addition to this, we added two overview visualizations called ListVis and TableVis to handle larger amounts of data and enable the user to select a subset. The different views are coordinated using linking and brushing and provide many different interaction possibilities.

To get more information on the usefulness of Gravi++ we conducted an extensive evaluation of our visualization. The first step was a usability evaluation to preclude that usability problems are mixed up with problems with the visualization method as such. After that we conducted an insight study, where we wanted to find the strength and limitations of supervised Machine Learning (ML) techniques, Exploratory Data Analysis (EDA), and Gravi++ for our problem domain. It indicates that Gravi++ is a very good method for analyzing this kind of data and that using ML, EDA and visualization methods in conjunction will very likely contribute to a deeper comprehension of the data to explore.

Stage

Method

Subjects

Aim

Collected Material

Usability

usability inspection

1 usability expert

spot most obvious glitches

31 usability problems

heuristic evaluation

27 semi-experts
in usability

in depth testing

447 reports documenting
576 problems (221 different)

focus groups

additional usability assessment

no new problems BUT
different perspective

Insight Study
(Gravi++, EDA, Machine Learning)

insight reports

33 domain novices

patterns of insight &
cognitive strategies

876 reports documenting
2166 insights

log files

used vis. options &
exploration strategies

56055 log file entries

focus groups

relativize findings &
aids correct interpretation

transcription of 3x 100min

Case Study

interviews

2 real users

feasibility & usefulness
in real life

transcription of 1x 60min

thinking aloud

notes on 1x 180min

Transferability

interviews

14 experts
of other domains

usefulness in other domains

transcription of 14x 60min

Different steps in our extensive evaluation study.

 

Publications

List of all papers of the in2vis project.

Publications

2006
Markus Rester, Margit Pohl, Klaus Hinum, S. Miksch, Christian Popow, Susanne Ohmann, Staven Banovic, "Methods for the Evaluation of an Interactive Info Vis Tool Supporting Exploratory Reasoning Processes", BEyond time and errors: novel evaLuation methods for Information Visualization (BELIV 2006) held in conjunction with Advanced Visual Interfaces (AVI-2006), International Working Conference, 2006. paper
2005
Markus Rester, Margit Pohl, Klaus Hinum, S. Miksch, Susanne Ohmann, Christian Popow, Staven Banovic, "{Assessing the Usability of an Interactive Information Visualization Method as the First Step of a Sustainable Evaluation}", Usability Symposium: Empowering Software Quality: How can Usability Engineering reach these goals?, vol. 198, pp. 31–43, 2005. paper
Klaus Hinum, S. Miksch, Wolfgang Aigner, Susanne Ohmann, Christian Popow, Margit Pohl, Markus Rester, "{Gravi++: Interactive Information Visualization of Highly Structured Temporal Data}", Workshop on Intelligent Data Analyis in Medicine and Pharmacology (IDAMAP-2005) in conjunction with the 10th Conference on Artificial Intelligence in Medicine in Europe (AIME 2005), pp. 67–72, 2005. paper
Klaus Hinum, S. Miksch, Wolfgang Aigner, Susanne Ohmann, Christian Popow, Margit Pohl, Markus Rester, "Gravi++: Interactive Information Visualization to Explore Highly Structured Temporal Data", Journal of Universal Computer Science, vol. 11, pp. 1792–1805, 2005. paper
2004
Christian Popow, Susanne Ohmann, Monika Lanzenberger, Herbert Herzog, B Schuch, S. Miksch, "{LINK-VIS, a Computer Program for Visualizing the Psychotherapeutical Process of Cognitive Behavioral Therapy (CBT)}", 16th World Congress of the International Association for Child and Adolescent Psychiatry and Allied Professions (IACAPAP), 2004.
1998
Christian Popow, L Kirchner, Werner Horn, Andreas Seyfang, S. Miksch, "{Klinische Erfahrungen mit einem wissensbasierten System zur Berechnung der parenteralen Ernährung von intensivbehandelten Früh- und Neugeborenen}", Symposium: Medizinische Experten- und wissensbasierte Systeme am AKH Wien, 1998.
1997
Christian Popow, S. Miksch, Werner Horn, F Paky, "{Clinical Intranet Applications at a Neonatal Intensive Care Unit}", , 1997.
1996
Christian Popow, Werner Horn, S. Miksch, "{VIE-Nmed: ein Programm für die Medikamentenverordnung an Neugeborenen-Intensivstationen}", Symposium: Medizinische Experten- und wissensbasierte Systeme am AKH Wien, 1996.