user interface adaptation based on user feedback and machine learning
TRANSCRIPT
![Page 1: User interface adaptation based on user feedback and machine learning](https://reader035.vdocuments.us/reader035/viewer/2022062523/58f17f9b1a28abf1198b4581/html5/thumbnails/1.jpg)
1
Presentation Outline
Motivation
Basic concept
Bakground
Futur work
Conclusion
Nesrine MEZHOUDI [email protected]
User Interface Adaptation Based on User Feedbacks and Machine
Learning
Louvain Interaction LabUniversité catholique de Louvain
Promoter:Prof. Jean Vanderdonckt
![Page 2: User interface adaptation based on user feedback and machine learning](https://reader035.vdocuments.us/reader035/viewer/2022062523/58f17f9b1a28abf1198b4581/html5/thumbnails/2.jpg)
2
Adaptation & User Centered Design
Not adapted & not User-centered UI
![Page 3: User interface adaptation based on user feedback and machine learning](https://reader035.vdocuments.us/reader035/viewer/2022062523/58f17f9b1a28abf1198b4581/html5/thumbnails/3.jpg)
3
Adaptation & User Centered Design
adapted & not User-centered UI
![Page 4: User interface adaptation based on user feedback and machine learning](https://reader035.vdocuments.us/reader035/viewer/2022062523/58f17f9b1a28abf1198b4581/html5/thumbnails/4.jpg)
4
Adaptation & User Centered Design
Adapted & User-centered UI
![Page 5: User interface adaptation based on user feedback and machine learning](https://reader035.vdocuments.us/reader035/viewer/2022062523/58f17f9b1a28abf1198b4581/html5/thumbnails/5.jpg)
5
Outline
Motivation
Basic conceptsMethods & Application
![Page 6: User interface adaptation based on user feedback and machine learning](https://reader035.vdocuments.us/reader035/viewer/2022062523/58f17f9b1a28abf1198b4581/html5/thumbnails/6.jpg)
6
Adaptation rules are staticAdaptation rules are implemented according to a predefined static set of standards, guidelines, and recommendations
Hardly re-adaptableBarely impossible to updateHighly expensive (redevelopment, time, human resources)
![Page 7: User interface adaptation based on user feedback and machine learning](https://reader035.vdocuments.us/reader035/viewer/2022062523/58f17f9b1a28abf1198b4581/html5/thumbnails/7.jpg)
7
Static rules prevent adaptation
• Dissatisfaction• Frustration• Discouragement• Loss of motivation• …
![Page 8: User interface adaptation based on user feedback and machine learning](https://reader035.vdocuments.us/reader035/viewer/2022062523/58f17f9b1a28abf1198b4581/html5/thumbnails/8.jpg)
8
Solution: Interaction-based adaptation
Objective:enhancing the end-user influence in the UI definition
![Page 9: User interface adaptation based on user feedback and machine learning](https://reader035.vdocuments.us/reader035/viewer/2022062523/58f17f9b1a28abf1198b4581/html5/thumbnails/9.jpg)
99
User
Interaction
Feedback
Feedback
analysis
Learning
Recommendation
![Page 10: User interface adaptation based on user feedback and machine learning](https://reader035.vdocuments.us/reader035/viewer/2022062523/58f17f9b1a28abf1198b4581/html5/thumbnails/10.jpg)
10
Principals typologies to express feedback
Implicit Feedback
Explicit Feedback
Without rating aims With rating aims
10
![Page 11: User interface adaptation based on user feedback and machine learning](https://reader035.vdocuments.us/reader035/viewer/2022062523/58f17f9b1a28abf1198b4581/html5/thumbnails/11.jpg)
11
Unified theoretical architecture for adaptation based on ML
Context• User• Platform• Environment
Adaptation Rules
Repository
Adaptation Management
Layer
Perception(tracking tools, sensors…
)
RecommendationFeedback
Reinforcemen
t
EvaluationUpdatin
g Adapting
Perc
eptio
n Lay
er
UI
![Page 12: User interface adaptation based on user feedback and machine learning](https://reader035.vdocuments.us/reader035/viewer/2022062523/58f17f9b1a28abf1198b4581/html5/thumbnails/12.jpg)
12
The Adaptation Rule Manager
Adaptation Rules
Repository
Trainer-Rule Engine
Learner-Rule Engine
Adaptation Rules Manager
Generated Rules
Rule Engine
Rule Management
Tools
Training Rules
Feedbacks User
![Page 13: User interface adaptation based on user feedback and machine learning](https://reader035.vdocuments.us/reader035/viewer/2022062523/58f17f9b1a28abf1198b4581/html5/thumbnails/13.jpg)
13
The Adaptation Rule Manager
Adaptation Rules
Repository
Trainer-Rule Engine
Learner-Rule Engine
Adaptation Rules Manager
Generated Rules
Rule Engine
Rule Management
Tools
Training Rules
Feedbacks User
(1) Executing pre-existed adaptation rules, serving as a training set to (2) detect a pattern of user behavior throughout his feedbacks. Besides, (3) coming up with statistics and (promote/demote) ranking for the Learner Rule Engine (RLE).
![Page 14: User interface adaptation based on user feedback and machine learning](https://reader035.vdocuments.us/reader035/viewer/2022062523/58f17f9b1a28abf1198b4581/html5/thumbnails/14.jpg)
14
The Adaptation Rule Manager
Adaptation Rules
Repository
Trainer-Rule Engine
Learner-Rule Engine
Adaptation Rules Manager
Generated Rules
Rule Engine
Rule Management
Tools
Training Rules
Feedbacks User
analyzing collected user judgments. Which are intended to serve in a promoting/demoting ranking, Then generate new decision rules , (Learns)
![Page 15: User interface adaptation based on user feedback and machine learning](https://reader035.vdocuments.us/reader035/viewer/2022062523/58f17f9b1a28abf1198b4581/html5/thumbnails/15.jpg)
Applications
15
Tasks
AUI
CUI
Final UI
![Page 16: User interface adaptation based on user feedback and machine learning](https://reader035.vdocuments.us/reader035/viewer/2022062523/58f17f9b1a28abf1198b4581/html5/thumbnails/16.jpg)
Applications
16
Tasks
AUI
CUI
Final UI
![Page 17: User interface adaptation based on user feedback and machine learning](https://reader035.vdocuments.us/reader035/viewer/2022062523/58f17f9b1a28abf1198b4581/html5/thumbnails/17.jpg)
17
Conclusion
State of the arts
Conceptualization
Implantation
Test & Evaluation
![Page 18: User interface adaptation based on user feedback and machine learning](https://reader035.vdocuments.us/reader035/viewer/2022062523/58f17f9b1a28abf1198b4581/html5/thumbnails/18.jpg)
18
Thank you for your attention.
Nesrine Mezhoudi