Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Visual Analytics Interfaces for Big Data Environments
1. 20. Runder Tisch der Technischen Visualistik
Visual Analytics
Interfaces for Big
Data Environments
17 April 2018 | Fakultät Informatik
Chair of Media Design
Technische Universität Dresden
Dietrich Kammer & Mandy Keck
2. Forschungsprojekt
VANDA - Visual Analytics Interfaces for Big Data Environments
Data Analytics,
Copyright Observation
Data Crawling, Content
Exploration
Data Analytics and
Text Mining for Smart
Adaptive Learning
Environments
Research on Human
Computer Interaction
and Information
Visualization
Purchasing Platform bet-
ween Businesses with
Millions of Products
www.vanda-project.de
20. RTTV 17. April 2018 Dietrich Kammer & Mandy Keck
3. Data Scientist Data Worker
End User Future Work
Investigate Clustering
Determine Parameters
Provide Ground Truth
Semi-supervised Learning
Transparency
Controllability
Explorability
Virtual Reality
Elastic Displays
4. Data Scientist[Wenskovitch et al. 2018]
Tasks
__ Explore alternate projections
__ Investigate clusters and features
__ Individual observations
__ Determining parameters for algorithms
__ Selection of pipelines for dimension reduction
and clustering
20. RTTV 17. April 2018 Dietrich Kammer & Mandy Keck
5. Data Scientist[Wenskovitch et al. 2018]
Tasks
__ Explore alternate projections
__ Investigate clusters and features
__ Individual observations
__ Determining parameters for algorithms
__ Selection of pipelines for dimension reduction
and clustering
HD DATA 2D DATA
Item 1
Item 2
Item 3
Dimension1
Dimension2
Dimension3
Dimension4
...
Item n
Dimension5
Dimensionn
...
Item 1
Item 2
Item 3
...
Item n
Dimension1
Dimension2
[Munzner 2014]
20. RTTV 17. April 2018 Dietrich Kammer & Mandy Keck
6. Data Scientist [Wenskovitch et al. 2018]
Tasks
__ Explore alternate projections
__ Investigate clusters and features
__ Individual observations
__ Determining parameters for algorithms
__ Selection of pipelines for dimension reduction
and clustering
20. RTTV 17. April 2018 Dietrich Kammer & Mandy Keck
7. Data Scientist [Wenskovitch et al. 2018]
Tasks
__ Explore alternate projections
__ Investigate clusters and features
__ Individual observations
__ Determining parameters for algorithms
__ Selection of pipelines for dimension reduction
and clustering
20. RTTV 17. April 2018 Dietrich Kammer & Mandy Keck
8. Data Scientist [Wenskovitch et al. 2018]
Tasks
__ Explore alternate projections
__ Investigate clusters and features
__ Individual observations
__ Determining parameters for algorithms
__ Selection of pipelines for dimension reduction
and clustering
Birch Algorithm
global local
K-Means Algorithm
global local
20. RTTV 17. April 2018 Dietrich Kammer & Mandy Keck
9. Data Scientist [Wenskovitch et al. 2018]
Tasks
__ Explore alternate projections
__ Investigate clusters and features
__ Individual observations
__ Determining parameters for algorithms
__ Selection of pipelines for dimension reduction
and clustering
[Wenskovitch et al. 2018]
20. RTTV 17. April 2018 Dietrich Kammer & Mandy Keck
10. Data Scientist [Wenskovitch et al. 2018]
Tasks
__ Explore alternate projections
__ Investigate clusters and features
__ Individual observations
__ Determining parameters for algorithms
__ Selection of pipelines for dimension reduction
and clustering
Visualization challenges
__ Overplotting
__ Filtering and grouping
20. RTTV 17. April 2018 Dietrich Kammer & Mandy Keck
11. Data Scientist [Wenskovitch et al. 2018]
Tasks
__ Explore alternate projections
__ Investigate clusters and features
__ Individual observations
__ Determining parameters for algorithms
__ Selection of pipelines for dimension reduction
and clustering
Visualization challenges
__ Overplotting
__ Filtering and grouping
20. RTTV 17. April 2018 Dietrich Kammer & Mandy Keck
12. Data Scientist [Wenskovitch et al. 2018]
Tasks
__ Explore alternate projections
__ Investigate clusters and features
__ Individual observations
__ Determining parameters for algorithms
__ Selection of pipelines for dimension reduction
and clustering
Visualization challenges
__ Overplotting
__ Filtering and grouping
20. RTTV 17. April 2018 Dietrich Kammer & Mandy Keck
13. Data Scientist [Wenskovitch et al. 2018]
Tasks
__ Explore alternate projections
__ Investigate clusters and features
__ Individual observations
__ Determining parameters for algorithms
__ Selection of pipelines for dimension reduction
and clustering
Visualization challenges
__ Overplotting
__ Filtering and grouping
Interaction
__ Parametric interaction
__ Observation-level interaction
__ Surface-level interaction
20. RTTV 17. April 2018 Dietrich Kammer & Mandy Keck
14. Data Scientist [Wenskovitch et al. 2018]
Tasks
__ Explore alternate projections
__ Investigate clusters and features
__ Individual observations
__ Determining parameters for algorithms
__ Selection of pipelines for dimension reduction
and clustering
Visualization challenges
__ Overplotting
__ Filtering and grouping
Interaction
__ Parametric interaction
__ Observation-level interaction
__ Surface-level interaction
20. RTTV 17. April 2018 Dietrich Kammer & Mandy Keck
15. Data Worker [Heimerl et al. 2012]
Challenge
__ Provide initial ground truth data
__ Support of semi-supervised machine
learning systems
__ Interactive record linkage
Approach
__ Very small units of work presented in the
most suitable way
__ Integrate gamification as a tool to make
the process more motivating for the user
20. RTTV 17. April 2018 Dietrich Kammer & Mandy Keck
16. End User - Recommender Systems
Facebook Netflix Youtube
Spotify Pinterest Booking.com
17. Visualization Challenges[He et al. 2016, Keck & Kammer 2018]
Visualization Challenges
__ Transparency
__ Explorability
__ Controllability
__ Context-Awareness
20. RTTV 17. April 2018 Dietrich Kammer & Mandy Keck
18. Visualization Challenges[Parra et al. 2014]
Visualization Challenges
__ Transparency
__ Explorability
__ Controllability
__ Context-Awareness
20. RTTV 17. April 2018 Dietrich Kammer & Mandy Keck
19. Visualization Challenges[Gansner et al. 2009]
Visualization Challenges
__ Transparency
__ Explorability
__ Controllability
__ Context-Awareness
20. RTTV 17. April 2018 Dietrich Kammer & Mandy Keck
20. Visualization Challenges[Kunkel et al. 2017]
Visualization Challenges
__ Transparency
__ Explorability
__ Controllability
__ Context-Awareness
20. RTTV 17. April 2018 Dietrich Kammer & Mandy Keck
21. Visualization Challenges[Bogdanov et al. 2013]
Visualization Challenges
__ Transparency
__ Explorability
__ Controllability
__ Context-Awareness
20. RTTV 17. April 2018 Dietrich Kammer & Mandy Keck
24. References (1)
[Bogdanov et al. 2013] D. Bogdanov, M. Haro, F. Fuhrmann, A. Xambó, E. Gómez, P. Herrera: Semantic audio content-based music recommendation
and visualization based on user preference examples, In Information Processing & Management, Volume 49, Issue 1, 2013,
Pages 13-33, ISSN 0306-4573, https://doi.org/10.1016/j.ipm.2012.06.004.
[He et al. 2016] C. He, D. Parra, K. Verbert: Interactive recommender systems: A survey of the state of the art and future research
challenges and opportunities, Expert Systems with Applications, Volume 56, 2016, Pages 9-27, ISSN 0957-4174,
https://doi.org/10.1016/j.eswa.2016.02.013.
[Gansner et al. 2009] E. Gansner, Y. Hu, S. Kobourov, and C. Volinsky: Putting recommendations on the map: visualizing clusters and
relations. In Proceedings of the third ACM conference on Recommender systems (RecSys ‚09). ACM, New York, NY, USA, 345-348.
2009. DOI=http://dx.doi.org/10.1145/1639714.1639784
[Heimerl et al. 2012] F. Heimerl, S. Koch, H. Bosch, T. Ertl: Visual Classifier Training for Text Document Retrieval. IEEE Transactions on
Visualization and Computer Graphics, Vol. 18, No. 12, 2012
[Kammer et al. 2017] D. Kammer, M. Keck, M. Müller, T. Gründer, R. Groh: Exploring Big Data Landscapes with Elastic Displays.
Mensch & Computer 2017 - Workshop Begreifbare Interaktion, Oldenbourg Verlag, Regensburg, Germany. 2017
[Keck & Kammer 2018] M. Keck & D. Kammer: On Visualization Challenges for Interactive Recommender Systems. AVI 2018 - VisBIA 2018 -
Workshop on Visual Interfaces for Big Data Environments in Industrial Applications, 2018 (in press)
[Kunkel et al. 2017] J. Kunkel, B. Loepp, and J. Ziegler: A 3D Item Space Visualization for Presenting and Manipulating User Preferences
in Collaborative Filtering. In Proceedings of the 22nd International Conference on Intelligent User Interfaces (IUI‘17). ACM,
New York, NY, USA, 3-15. 2017. DOI: https://doi.org/10.1145/3025171.3025189
20. RTTV 17. April 2018 Dietrich Kammer & Mandy Keck
25. [Munzner 2014] T. Munzner: Visualization Analysis and Design. A.K. Peters visualization series. ISBN 978-1-466-50891-0. 2014
http://www.cs.ubc.ca/~tmm/vadbook
[Parra et al. 2014] D. Parra, P. Brusilovsky, and C. Trattner. 2014. See what you want to see: visual user-driven approach for hybrid
recommendation. In Proceedings of the 19th international conference on Intelligent User Interfaces (IUI ‚14). ACM, New York,
NY, USA, 235-240. DOI: http://dx.doi.org/10.1145/2557500.2557542
[Wenskovitch et al. 2018] J. Wenskovitch, I. Crandell, N. Ramakrishnan, L. House, S. Leman, C. North: Towards a Systematic Combination of Dimension
Reduction and Clustering in Visual Analytics. IEEE Trans Vis Comput Graph. 2018 Jan, 24(1): 131-141. 2018.
doi: 10.1109/TVCG.2017.2745258.
References (2)
20. RTTV 17. April 2018 Dietrich Kammer & Mandy Keck