debugging and hacking the user
DESCRIPTION
Debugging and Hacking the User. Remco Chang Assistant Professor Tufts University. “Let the Data Talk to You”. Domain-Specific Visual Analytics Systems. Political Simulation Agent-based analysis With DARPA Wire Fraud Detection With Bank of America Bridge Maintenance With US DOT - PowerPoint PPT PresentationTRANSCRIPT
![Page 1: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/1.jpg)
Intro Goal Crowd Prediction Wrap-up1/26 Learning
Debugging and Hacking the User
Remco Chang
Assistant ProfessorTufts University
![Page 2: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/2.jpg)
Intro Goal Crowd Prediction Wrap-up2/26 Learning
“Let the Data Talk to You”
![Page 3: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/3.jpg)
Intro Goal Crowd Prediction Wrap-up3/26 Learning
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
comparisonR. Chang et al., Two Visualization Tools for Analysis of Agent-Based Simulations in Political Science. IEEE CG&A, 2012
![Page 4: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/4.jpg)
Intro Goal Crowd Prediction Wrap-up4/26 Learning
Domain-Specific Visual Analytics Systems
R. Chang et al., WireVis: Visualization of Categorical, Time-Varying Data From Financial Transactions, VAST 2008.
• 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
![Page 5: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/5.jpg)
Intro Goal Crowd Prediction Wrap-up5/26 Learning
Domain-Specific Visual Analytics Systems
R. Chang et al., An Interactive Visual Analytics System for Bridge Management, Journal of Computer Graphics Forum, 2010. To Appear.
• 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
![Page 6: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/6.jpg)
Intro Goal Crowd Prediction Wrap-up6/26 Learning
Domain-Specific Visual Analytics Systems
R. Chang et al., Interactive Coordinated Multiple-View Visualization of Biomechanical Motion Data , IEEE Vis (TVCG) 2009.
• 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
![Page 7: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/7.jpg)
Intro Goal Crowd Prediction Wrap-up7/26 Learning
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
![Page 8: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/8.jpg)
Intro Goal Crowd Prediction Wrap-up8/26 Learning
Human + Computer
![Page 9: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/9.jpg)
Intro Goal Crowd Prediction Wrap-up9/26 Learning
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
![Page 10: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/10.jpg)
Intro Goal Crowd Prediction Wrap-up10/26 Learning
What is in a User’s Interactions?
• 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?
Visualization HumanOutput
Input
Keyboard, Mouse, etc
Images (monitor)
![Page 11: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/11.jpg)
Intro Goal Crowd Prediction Wrap-up11/26 Learning
CrowdSourcing
Can we leverage multiple user’s past histories?
![Page 12: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/12.jpg)
Intro Goal Crowd Prediction Wrap-up12/26 Learning
Example 1: Crowdsourcing
• Scented Widget (Willet et al. 2007)
![Page 13: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/13.jpg)
Intro Goal Crowd Prediction Wrap-up13/26 Learning
Example 1: Scented Widget
![Page 14: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/14.jpg)
Intro Goal Crowd Prediction Wrap-up14/26 Learning
Model learning from user’s interactions
How do we help a user define a (weighted) distance metric?
![Page 15: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/15.jpg)
Intro Goal Crowd Prediction Wrap-up15/26 Learning
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?
![Page 16: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/16.jpg)
Intro Goal Crowd Prediction Wrap-up16/26 Learning
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
![Page 17: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/17.jpg)
Intro Goal Crowd Prediction Wrap-up17/26 Learning
Dis-Function
R. Chang et al., Find Distance Function, Hide Model Inference. IEEE VAST Poster 2011R. Chang et al., Dis-function: Learning Distance Functions Interactively, IEEE VAST 2012.
Optimization:
![Page 18: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/18.jpg)
Intro Goal Crowd Prediction Wrap-up18/26 Learning
Predicting User’s Behavior
Can we predict how well the user will do in a visual search task?
![Page 19: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/19.jpg)
Intro Goal Crowd Prediction Wrap-up19/26 Learning
Task: Find Waldo
• Google-Maps style interface– Left, Right, Up, Down, Zoom In, Zoom Out, Found
![Page 20: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/20.jpg)
Intro Goal Crowd Prediction Wrap-up20/26 Learning
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
![Page 21: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/21.jpg)
Intro Goal Crowd Prediction Wrap-up21/26 Learning
Analysis 1: Mouse Movement
![Page 22: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/22.jpg)
Intro Goal Crowd Prediction Wrap-up22/26 Learning
Analysis 2: Interaction Sequences
• Uses a combination of n-grams and decision tree
0 100 200 300 400 500 600 700 8000
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
Number of Interactions
Accu
racy
![Page 23: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/23.jpg)
Intro Goal Crowd Prediction Wrap-up23/26 Learning
Detecting User’s Characteristic
• We can detect a faint signal on the user’s personality traits…
0 100 200 300 400 500 600 700 8000
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
Neuroticism
Number of Interactions
Accu
racy
![Page 24: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/24.jpg)
Intro Goal Crowd Prediction Wrap-up24/26 Learning
Possible Implications
• A note on “Paired Analytics”– A PA user needs to do everything!– Paired analysis reduces cognitive workload
![Page 25: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/25.jpg)
Intro Goal Crowd Prediction Wrap-up25/26 Learning
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…
![Page 27: Debugging and Hacking the User](https://reader034.vdocument.in/reader034/viewer/2022051402/56816405550346895dd5ac93/html5/thumbnails/27.jpg)
Intro Goal Crowd Prediction Wrap-up27/26 Learning
Backup