Domain-Specific Visual Analytics Systems: Exploring Expert User Insights

This presentation delves into domain-specific visual analytics systems focusing on political simulation, wire fraud detection, bridge maintenance, and more. It emphasizes leveraging user expertise for effective system design and evaluation, highlighting the importance of user insights in data analysis. The content showcases various visualization tools and interactive systems developed for different applications, underscoring the user-centric approach in enhancing analytical processes.

• Visual Analytics
• User Insights
• Data Analysis
• Interactive Systems
• System Design

rite_da Follow

Uploaded on Sep 08, 2024 | 0 Views

Download Presentation

Please find below an Image/Link to download the presentation.

The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. Download presentation by click this link. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.

Presentation Transcript

1. Intro Goal Crowd Learning Prediction Wrap-up 1/26 Debugging and Hacking the User Remco Chang Assistant Professor Tufts University

2. Intro Goal Crowd Learning Prediction Wrap-up 2/26 Let the Data Talk to You

3. Intro Goal Crowd Learning Prediction Wrap-up 3/26 Domain-Specific Visual Analytics Systems Political Simulation Agent-based analysis With DARPA Wire Fraud Detection With Bank of America Bridge Maintenance With US DOT Exploring inspection reports Biomechanical Motion Interactive motion comparison R. Chang et al., Two Visualization Tools for Analysis of Agent-Based Simulations in Political Science. IEEE CG&A, 2012

4. Intro Goal Crowd Learning Prediction Wrap-up 4/26 Domain-Specific Visual Analytics Systems Political Simulation Agent-based analysis With DARPA Wire Fraud Detection With Bank of America Bridge Maintenance With US DOT Exploring inspection reports Biomechanical Motion Interactive motion comparison R. Chang et al., WireVis: Visualization of Categorical, Time-Varying Data From Financial Transactions, VAST 2008.

5. Intro Goal Crowd Learning Prediction Wrap-up 5/26 Domain-Specific Visual Analytics Systems Political Simulation Agent-based analysis With DARPA Wire Fraud Detection With Bank of America Bridge Maintenance With US DOT Exploring inspection reports Biomechanical Motion Interactive motion comparison R. Chang et al., An Interactive Visual Analytics System for Bridge Management, Journal of Computer Graphics Forum,2010. To Appear.

6. Intro Goal Crowd Learning Prediction Wrap-up 6/26 Domain-Specific Visual Analytics Systems Political Simulation Agent-based analysis With DARPA Wire Fraud Detection With Bank of America Bridge Maintenance With US DOT Exploring inspection reports Biomechanical Motion Interactive motion comparison R. Chang et al., Interactive Coordinated Multiple-View Visualization of Biomechanical Motion Data, IEEE Vis (TVCG) 2009.

7. Intro Goal Crowd Learning Prediction Wrap-up 7/26 The User is NOT the Enemy Vis design starts with user and task analyses. However, When no two users are exactly the same, (expert-based) design is very difficult Evaluation is correspondingly very difficult (WireVis evaluation) Time to insight is very much user dependent Users are the domain experts They can provide a lot of information Question is how to harvest and leverage it

8. Intro Goal Crowd Learning Prediction Wrap-up 8/26 Human + Computer

9. Intro Goal Crowd Learning Prediction Wrap-up 9/26 Making the Users Work For You (Without Them Realizing that They Are) Examples Crowdsourcing Model learning from user s interactions Predict the user s behavior

10. Intro Goal Crowd Learning Prediction Wrap-up 10/26 What is in a User s Interactions? Keyboard, Mouse, etc Input Visualization Human Output Images (monitor) Types of Human-Visualization Interactions Word editing (input heavy, little output) Browsing, watching a movie (output heavy, little input) Visual Analysis (closer to 50-50) Challenge: Can we capture and extract a user s reasoning and intent through capturing a user s interactions?

11. Intro Goal Crowd Learning Prediction Wrap-up 11/26 CrowdSourcing Can we leverage multiple user s past histories?

12. Intro Goal Crowd Learning Prediction Wrap-up 12/26 Example 1: Crowdsourcing Scented Widget (Willet et al. 2007)

13. Intro Goal Crowd Learning Prediction Wrap-up 13/26 Example 1: Scented Widget

14. Intro Goal Crowd Learning Prediction Wrap-up 14/26 Model learning from user s interactions How do we help a user define a (weighted) distance metric?

15. Intro Goal Crowd Learning Prediction Wrap-up 15/26 Example 2: Metric Learning Finding the weights to a linear distance function Instead of a user manually give the weights, can we learn them implicitly through their interactions?

16. Intro Goal Crowd Learning Prediction Wrap-up 16/26 Example 2: Metric Learning In a projection space (e.g., MDS), the user directly moves points on the 2D plane that don t look right Until the expert is happy (or the visualization can not be improved further) The system learns the weights (importance) of each of the original k dimensions

17. Intro Goal Crowd Learning Prediction Wrap-up 17/26 Dis-Function Optimization: R. Chang et al., Find Distance Function, Hide Model Inference. IEEE VAST Poster 2011 R. Chang et al., Dis-function: Learning Distance Functions Interactively, IEEE VAST 2012.

18. Intro Goal Crowd Learning Prediction Wrap-up 18/26 Predicting User s Behavior Can we predict how well the user will do in a visual search task?

19. Intro Goal Crowd Learning Prediction Wrap-up 19/26 Task: Find Waldo Google-Maps style interface Left, Right, Up, Down, Zoom In, Zoom Out, Found

20. Intro Goal Crowd Learning Prediction Wrap-up 20/26 Classifying Users Collect two types of data about the user in real-time Physical mouse movement Mouse position, velocity, acceleration, angle change, distance, etc. Interaction sequences Sequences of button clicks 7 possible symbols Goal: Predict if a user will find Waldo within 500 seconds

21. Intro Goal Crowd Learning Prediction Wrap-up 21/26 Analysis 1: Mouse Movement

22. Intro Goal Crowd Learning Prediction Wrap-up 22/26 Analysis 2: Interaction Sequences Uses a combination of n-grams and decision tree 0.9 0.8 0.7 0.6 Accuracy 0.5 0.4 0.3 0.2 0.1 0 0 100 200 300 400 500 600 700 800 Number of Interactions

23. Intro Goal Crowd Learning Prediction Wrap-up 23/26 Detecting User s Characteristic We can detect a faint signal on the user s personality traits Neuroticism 0.8 0.7 0.6 Accuracy 0.5 0.4 0.3 0.2 0.1 0 0 100 200 300 400 500 600 700 800 Number of Interactions

24. Intro Goal Crowd Learning Prediction Wrap-up 24/26 Possible Implications A note on Paired Analytics A PA user needs to do everything! Paired analysis reduces cognitive workload

25. Intro Goal Crowd Learning Prediction Wrap-up 25/26 Conclusion Users are very valuable commodity. Leverage their domain knowledge!! Like the analysts who gained experience and knowledge, the computer can get smarter too!! Hacking the user can be done unobtrusively, and there s a lot of signal in their interaction trails

26. Intro Goal Crowd Learning Prediction Wrap-up 26/26 Thank you! Remco Chang remco@cs.tufts.edu

27. Intro Goal Crowd Learning Prediction Wrap-up 27/26 Backup