SlideShare a Scribd company logo
Visualization of ExplanationsVisualization of Explanations
inin
Recommender SystemsRecommender Systems
Seifedine KadrySeifedine Kadry
American University of The Middle East -American University of The Middle East -
KuwaitKuwait
Mohammed Z. Al-TaieMohammed Z. Al-Taie
AL-Salam University CollegeAL-Salam University College
-- Iraq ---- Iraq --
2
Goal of the studyGoal of the study
 The focus of this study is the visualization of explanations in
recommender systems.
 The study falls in the area of controlling the recommendation
process which gained little attention so far.
 Certain modalities (such as text, graphs, tables, and images)
can better present recommendations and explanations to
users.
3
4
What Are Recommender System (RS)?What Are Recommender System (RS)?
 Also called Recommendation Systems, they are
software tools and techniques providing
suggestions for items to be of use to a user.
BenefitsBenefits
 RS are being well used in various application
domains such as music, videos, queries, news,
friends on social networks etc..
5
Ex: Amazon’s Recommendation SystemEx: Amazon’s Recommendation System
A number of ways have been devised to offer
recommendations to the system users:
6
How Recommendations Are GivenHow Recommendations Are Given
7
Explanations in Recommender SystemExplanations in Recommender System
Now let’s talk about Explanations:
 Important pieces of information that are used by
both selling and buying agents to increase their
performance.
 Another definition … it is a description that makes
users better realize if the recommended item is
relevant to their needs or not.
8
YouTube
Explanation System
A Restaurant
Recommendation Explanation
Explanations - ExamplesExplanations - Examples
9
Amazon
Explanation System
Explanations - ExampleExplanations - Example
10
Why Using Explanations in RSWhy Using Explanations in RS??
11
 More on this artist …
 Try something from similar
artists …
 Someone similar to you also
like this …
 As you listened to that, you
may want this …
 These two go together …
 This is highly rated …
 Try something new …
 Similar or related products
…
 Complementary
accessories ...
 Gift idea ...
 Welcome back (recently
viewed) …
 For you today …
 New for you …
 Hot / Most popular of this
type …
 Other people also do this
…
Phrases Expressing ExplanationsPhrases Expressing Explanations
12
13
Information VisualizationInformation Visualization
 Human eyes can interpret a graph much faster than
plain texts, as it can process many visual cues
simultaneously.
 The design look of the website is what visitors care
much about compared to other website features such
as information structure, information focus and
usefulness of information.
 Visualization has been used in recommender systems
in both offering recommendation to users and
explaining why these recommendations were given.
14
Visualization TechniquesVisualization Techniques
To visualize information, a number of visualization
techniques have been used such as tables, images,
diagrams, text-highlighting, color schemes, rating and
animation. More sophisticated methods include:
Geometrically-transformed displays include techniques such as
scatterplot matrices, projection pursuit techniques, prosection views,
hyperslice and parallel coordinates
Iconic displays include little faces, needle icons, star icons, stick figure
icons, color icons and TileBars.
Dense pixel displays include techniques such as recursive patterns
and circle segments
Stacked displays include dimensional stacking.
In Amazon’s website, there is the use of techniques such
as text-highlighting, five-star rating scales, images,
colors, text size, tables, animation…
15
Example #1:Example #1:
16
a ten-star rating scale: The IMDb.com system uses
Example #2:Example #2:
An example for using different visualization techniques
in some explanations interface
17
Example #3:Example #3:
However, information visualization suffers from the
following common problems:
 Clutter
 Data overload
 Size of the graph
 Time complexity
18
Visualization ProblemsVisualization Problems
19
Correlated DisciplinesCorrelated Disciplines
A. Decision Making
 Decision making is the selection of a course of action from two or more
alternatives in order to solve a problem or to achieve an objective.
 It was found that the format of the information presented can affect
what decisions consumers can make.
 The integration of recommendation technologies with a profound
realization of human decision making can improve the quality of
recommendation for users and the predictability of decision outcomes.
There is strong a relationship between visualization of
information and two other disciplines. Understanding this
relationship is important for a better RS design:
B. Human Computer Interaction
 Human Computer Interaction (HCI) is concerned with how people
interact with computers and how computers can be developed for
successful interaction with human beings.
 The goal of HCI is to design systems that minimize the barrier between
the human's cognitive model of what they want to accomplish and the
computer's understanding of the user's task.
 By designing a good explanation interface, we can better explain
recommendations and can even push users to make further requests.
20
Correlated DisciplinesCorrelated Disciplines
21
There are a number of future research directions we
would like to explore. For example:
Future DirectionsFuture Directions
THANK YOU!

More Related Content

What's hot

What's hot (20)

The art technique of data visualization
The art  technique of data visualizationThe art  technique of data visualization
The art technique of data visualization
 
Demystifying Data Science with an introduction to Machine Learning
Demystifying Data Science with an introduction to Machine LearningDemystifying Data Science with an introduction to Machine Learning
Demystifying Data Science with an introduction to Machine Learning
 
Big Data Analytics
Big Data AnalyticsBig Data Analytics
Big Data Analytics
 
Presentation on Big Data Analytics
Presentation on Big Data AnalyticsPresentation on Big Data Analytics
Presentation on Big Data Analytics
 
Introduction to data science intro,ch(1,2,3)
Introduction to data science intro,ch(1,2,3)Introduction to data science intro,ch(1,2,3)
Introduction to data science intro,ch(1,2,3)
 
Visual Analytics in Big Data
Visual Analytics in Big DataVisual Analytics in Big Data
Visual Analytics in Big Data
 
Challenges in business analytics
Challenges in business analyticsChallenges in business analytics
Challenges in business analytics
 
The Evolution of Data Science
The Evolution of Data ScienceThe Evolution of Data Science
The Evolution of Data Science
 
Big Data Science: Intro and Benefits
Big Data Science: Intro and BenefitsBig Data Science: Intro and Benefits
Big Data Science: Intro and Benefits
 
Introduction to Data Science
Introduction to Data ScienceIntroduction to Data Science
Introduction to Data Science
 
Creating a Data Science Ecosystem for Scientific, Societal and Educational Im...
Creating a Data Science Ecosystem for Scientific, Societal and Educational Im...Creating a Data Science Ecosystem for Scientific, Societal and Educational Im...
Creating a Data Science Ecosystem for Scientific, Societal and Educational Im...
 
Introduction to data science
Introduction to data scienceIntroduction to data science
Introduction to data science
 
Introduction to Big Data/Machine Learning
Introduction to Big Data/Machine LearningIntroduction to Big Data/Machine Learning
Introduction to Big Data/Machine Learning
 
Big Data Presentation - Data Center Dynamics Sydney 2014 - Dez Blanchfield
Big Data Presentation - Data Center Dynamics Sydney 2014 - Dez BlanchfieldBig Data Presentation - Data Center Dynamics Sydney 2014 - Dez Blanchfield
Big Data Presentation - Data Center Dynamics Sydney 2014 - Dez Blanchfield
 
Use case and integration of ClickHouse with Apache Superset & Dremio
Use case and integration of ClickHouse with Apache Superset & DremioUse case and integration of ClickHouse with Apache Superset & Dremio
Use case and integration of ClickHouse with Apache Superset & Dremio
 
GTU GeekDay Data Science and Applications
GTU GeekDay Data Science and ApplicationsGTU GeekDay Data Science and Applications
GTU GeekDay Data Science and Applications
 
EDF2013: Big Data Tutorial: Marko Grobelnik
EDF2013: Big Data Tutorial: Marko GrobelnikEDF2013: Big Data Tutorial: Marko Grobelnik
EDF2013: Big Data Tutorial: Marko Grobelnik
 
Machine Learning - Challenges, Learnings & Opportunities
Machine Learning - Challenges, Learnings & OpportunitiesMachine Learning - Challenges, Learnings & Opportunities
Machine Learning - Challenges, Learnings & Opportunities
 
Data science presentation 2nd CI day
Data science presentation 2nd CI dayData science presentation 2nd CI day
Data science presentation 2nd CI day
 
Big data(1st presentation)
Big data(1st presentation)Big data(1st presentation)
Big data(1st presentation)
 

Similar to Visualization of explanations in recommender systems

System Development Overview Assignment 3
System Development Overview Assignment 3System Development Overview Assignment 3
System Development Overview Assignment 3
Ashley Fisher
 
Final wireframes from screen concept to user interaction v0.4
Final wireframes  from screen concept to user interaction v0.4Final wireframes  from screen concept to user interaction v0.4
Final wireframes from screen concept to user interaction v0.4
Mia Horrigan
 
Explanations in Recommender Systems: Overview and Research Approaches
Explanations in Recommender Systems: Overview and Research ApproachesExplanations in Recommender Systems: Overview and Research Approaches
Explanations in Recommender Systems: Overview and Research Approaches
Universiti Technologi Malaysia (UTM)
 
Requirements Definitions Of The Geospatial Web
Requirements Definitions Of The Geospatial WebRequirements Definitions Of The Geospatial Web
Requirements Definitions Of The Geospatial Web
Michael Maclennan
 
Strengths And Weaknesses Of Software Development
Strengths And Weaknesses Of Software DevelopmentStrengths And Weaknesses Of Software Development
Strengths And Weaknesses Of Software Development
Brianna Johnson
 
Recommender System in light of Big Data
Recommender System in light of Big DataRecommender System in light of Big Data
Recommender System in light of Big Data
Khadija Atiya
 
Technology in Education & The Internet
Technology in Education& The InternetTechnology in Education& The Internet
Technology in Education & The Internet
CARLOS MARTINEZ
 

Similar to Visualization of explanations in recommender systems (20)

Sweeny group think-ias2015
Sweeny group think-ias2015Sweeny group think-ias2015
Sweeny group think-ias2015
 
System Development Overview Assignment 3
System Development Overview Assignment 3System Development Overview Assignment 3
System Development Overview Assignment 3
 
Methods for analysis and design of an information system.pdf
Methods for analysis and design of an information system.pdfMethods for analysis and design of an information system.pdf
Methods for analysis and design of an information system.pdf
 
ADV: Solving the data visualization dilemma
ADV: Solving the data visualization dilemmaADV: Solving the data visualization dilemma
ADV: Solving the data visualization dilemma
 
Designing Interactions / Experiences: Lecture #04
 Designing Interactions / Experiences: Lecture #04 Designing Interactions / Experiences: Lecture #04
Designing Interactions / Experiences: Lecture #04
 
Final wireframes from screen concept to user interaction v0.4
Final wireframes  from screen concept to user interaction v0.4Final wireframes  from screen concept to user interaction v0.4
Final wireframes from screen concept to user interaction v0.4
 
Explanations in Recommender Systems: Overview and Research Approaches
Explanations in Recommender Systems: Overview and Research ApproachesExplanations in Recommender Systems: Overview and Research Approaches
Explanations in Recommender Systems: Overview and Research Approaches
 
Requirements Definitions Of The Geospatial Web
Requirements Definitions Of The Geospatial WebRequirements Definitions Of The Geospatial Web
Requirements Definitions Of The Geospatial Web
 
Review on Opinion Targets and Opinion Words Extraction Techniques from Online...
Review on Opinion Targets and Opinion Words Extraction Techniques from Online...Review on Opinion Targets and Opinion Words Extraction Techniques from Online...
Review on Opinion Targets and Opinion Words Extraction Techniques from Online...
 
Product Analyst Advisor
Product Analyst AdvisorProduct Analyst Advisor
Product Analyst Advisor
 
Strengths And Weaknesses Of Software Development
Strengths And Weaknesses Of Software DevelopmentStrengths And Weaknesses Of Software Development
Strengths And Weaknesses Of Software Development
 
World Usability Day 2014 - UX Toolbelt for Developers
World Usability Day 2014 - UX Toolbelt for DevelopersWorld Usability Day 2014 - UX Toolbelt for Developers
World Usability Day 2014 - UX Toolbelt for Developers
 
Useful interactions
Useful interactionsUseful interactions
Useful interactions
 
Recommender system and big data (design a smartphone recommender system based...
Recommender system and big data (design a smartphone recommender system based...Recommender system and big data (design a smartphone recommender system based...
Recommender system and big data (design a smartphone recommender system based...
 
Recommender System in light of Big Data
Recommender System in light of Big DataRecommender System in light of Big Data
Recommender System in light of Big Data
 
Technology in Education & The Internet
Technology in Education& The InternetTechnology in Education& The Internet
Technology in Education & The Internet
 
User Experience & Design…Designing for others…UED
User Experience & Design…Designing for others…UEDUser Experience & Design…Designing for others…UED
User Experience & Design…Designing for others…UED
 
IRJET- Implementing Social CRM System for an Online Grocery Shopping Platform...
IRJET- Implementing Social CRM System for an Online Grocery Shopping Platform...IRJET- Implementing Social CRM System for an Online Grocery Shopping Platform...
IRJET- Implementing Social CRM System for an Online Grocery Shopping Platform...
 
IRJET- Strength and Workability of High Volume Fly Ash Self-Compacting Concre...
IRJET- Strength and Workability of High Volume Fly Ash Self-Compacting Concre...IRJET- Strength and Workability of High Volume Fly Ash Self-Compacting Concre...
IRJET- Strength and Workability of High Volume Fly Ash Self-Compacting Concre...
 
Recommendation system (1).pptx
Recommendation system (1).pptxRecommendation system (1).pptx
Recommendation system (1).pptx
 

More from Universiti Technologi Malaysia (UTM)

Factors disrupting a successful implementation of e-commerce in iraq
Factors disrupting a successful implementation of e-commerce in iraqFactors disrupting a successful implementation of e-commerce in iraq
Factors disrupting a successful implementation of e-commerce in iraq
Universiti Technologi Malaysia (UTM)
 

More from Universiti Technologi Malaysia (UTM) (10)

A self organizing communication model for disaster risk management
A self organizing communication model for disaster risk managementA self organizing communication model for disaster risk management
A self organizing communication model for disaster risk management
 
Spark Working Environment in Windows OS
Spark Working Environment in Windows OSSpark Working Environment in Windows OS
Spark Working Environment in Windows OS
 
Python networkx library quick start guide
Python networkx library quick start guidePython networkx library quick start guide
Python networkx library quick start guide
 
Python 3.x quick syntax guide
Python 3.x quick syntax guidePython 3.x quick syntax guide
Python 3.x quick syntax guide
 
Social media with big data analytics
Social media with big data analyticsSocial media with big data analytics
Social media with big data analytics
 
Predicting the relevance of search results for e-commerce systems
Predicting the relevance of search results for e-commerce systemsPredicting the relevance of search results for e-commerce systems
Predicting the relevance of search results for e-commerce systems
 
Scientific theory of state and society parities and disparities between the p...
Scientific theory of state and society parities and disparities between the p...Scientific theory of state and society parities and disparities between the p...
Scientific theory of state and society parities and disparities between the p...
 
Nation building current trends of technology use in da’wah
Nation building current trends of technology use in da’wahNation building current trends of technology use in da’wah
Nation building current trends of technology use in da’wah
 
Flight MH370 community structure
Flight MH370 community structureFlight MH370 community structure
Flight MH370 community structure
 
Factors disrupting a successful implementation of e-commerce in iraq
Factors disrupting a successful implementation of e-commerce in iraqFactors disrupting a successful implementation of e-commerce in iraq
Factors disrupting a successful implementation of e-commerce in iraq
 

Recently uploaded

Grow Your Instagram Profile Organically A Guide to Real Engagement.pdf
Grow Your Instagram Profile Organically A Guide to Real Engagement.pdfGrow Your Instagram Profile Organically A Guide to Real Engagement.pdf
Grow Your Instagram Profile Organically A Guide to Real Engagement.pdf
SocioCosmos
 
“To be integrated is to feel secure, to feel connected.” The views and experi...
“To be integrated is to feel secure, to feel connected.” The views and experi...“To be integrated is to feel secure, to feel connected.” The views and experi...
“To be integrated is to feel secure, to feel connected.” The views and experi...
AJHSSR Journal
 
How to blow up on social media simple di
How to blow up on social media simple diHow to blow up on social media simple di
How to blow up on social media simple di
RachaelOnuche
 

Recently uploaded (16)

Want to Amplify Your Pinterest Content?...
Want to Amplify Your Pinterest Content?...Want to Amplify Your Pinterest Content?...
Want to Amplify Your Pinterest Content?...
 
Call Girls Dehradun | ₹,9500 Pay Cash 9719300533 Free Home Delivery Escorts S...
Call Girls Dehradun | ₹,9500 Pay Cash 9719300533 Free Home Delivery Escorts S...Call Girls Dehradun | ₹,9500 Pay Cash 9719300533 Free Home Delivery Escorts S...
Call Girls Dehradun | ₹,9500 Pay Cash 9719300533 Free Home Delivery Escorts S...
 
LORRAINE ANDREI_LEQUIGAN_HOW TO USE TRELLO.pptx
LORRAINE ANDREI_LEQUIGAN_HOW TO USE TRELLO.pptxLORRAINE ANDREI_LEQUIGAN_HOW TO USE TRELLO.pptx
LORRAINE ANDREI_LEQUIGAN_HOW TO USE TRELLO.pptx
 
Multilingual SEO Services | Multilingual Keyword Research | Filose
Multilingual SEO Services |  Multilingual Keyword Research | FiloseMultilingual SEO Services |  Multilingual Keyword Research | Filose
Multilingual SEO Services | Multilingual Keyword Research | Filose
 
Non-Financial Information and Firm Risk Non-Financial Information and Firm Risk
Non-Financial Information and Firm Risk Non-Financial Information and Firm RiskNon-Financial Information and Firm Risk Non-Financial Information and Firm Risk
Non-Financial Information and Firm Risk Non-Financial Information and Firm Risk
 
Social Media kdjhadhnjbdsjbdff fjkjasfkl
Social Media kdjhadhnjbdsjbdff fjkjasfklSocial Media kdjhadhnjbdsjbdff fjkjasfkl
Social Media kdjhadhnjbdsjbdff fjkjasfkl
 
Children's Data Privacy_April-22_2024.pdf
Children's Data Privacy_April-22_2024.pdfChildren's Data Privacy_April-22_2024.pdf
Children's Data Privacy_April-22_2024.pdf
 
7 Tips on Social Media Marketing strategy
7 Tips on Social Media Marketing strategy7 Tips on Social Media Marketing strategy
7 Tips on Social Media Marketing strategy
 
How social media marketing helps businesses in 2024.pdf
How social media marketing helps businesses in 2024.pdfHow social media marketing helps businesses in 2024.pdf
How social media marketing helps businesses in 2024.pdf
 
Grow Your Instagram Profile Organically A Guide to Real Engagement.pdf
Grow Your Instagram Profile Organically A Guide to Real Engagement.pdfGrow Your Instagram Profile Organically A Guide to Real Engagement.pdf
Grow Your Instagram Profile Organically A Guide to Real Engagement.pdf
 
“To be integrated is to feel secure, to feel connected.” The views and experi...
“To be integrated is to feel secure, to feel connected.” The views and experi...“To be integrated is to feel secure, to feel connected.” The views and experi...
“To be integrated is to feel secure, to feel connected.” The views and experi...
 
Top 10 Best Motivational Movies Of Bollywood
Top 10 Best Motivational Movies Of BollywoodTop 10 Best Motivational Movies Of Bollywood
Top 10 Best Motivational Movies Of Bollywood
 
Looking to Drive Traffic from Pinterest?
Looking to Drive Traffic from Pinterest?Looking to Drive Traffic from Pinterest?
Looking to Drive Traffic from Pinterest?
 
Get Ahead with YouTube Growth Services....
Get Ahead with YouTube Growth Services....Get Ahead with YouTube Growth Services....
Get Ahead with YouTube Growth Services....
 
How to blow up on social media simple di
How to blow up on social media simple diHow to blow up on social media simple di
How to blow up on social media simple di
 
Experience genuine and sustainable growth on TikTok.
Experience genuine and sustainable growth on TikTok.Experience genuine and sustainable growth on TikTok.
Experience genuine and sustainable growth on TikTok.
 

Visualization of explanations in recommender systems

  • 1. Visualization of ExplanationsVisualization of Explanations inin Recommender SystemsRecommender Systems Seifedine KadrySeifedine Kadry American University of The Middle East -American University of The Middle East - KuwaitKuwait Mohammed Z. Al-TaieMohammed Z. Al-Taie AL-Salam University CollegeAL-Salam University College -- Iraq ---- Iraq --
  • 2. 2 Goal of the studyGoal of the study  The focus of this study is the visualization of explanations in recommender systems.  The study falls in the area of controlling the recommendation process which gained little attention so far.  Certain modalities (such as text, graphs, tables, and images) can better present recommendations and explanations to users.
  • 3. 3
  • 4. 4 What Are Recommender System (RS)?What Are Recommender System (RS)?  Also called Recommendation Systems, they are software tools and techniques providing suggestions for items to be of use to a user. BenefitsBenefits  RS are being well used in various application domains such as music, videos, queries, news, friends on social networks etc..
  • 5. 5 Ex: Amazon’s Recommendation SystemEx: Amazon’s Recommendation System
  • 6. A number of ways have been devised to offer recommendations to the system users: 6 How Recommendations Are GivenHow Recommendations Are Given
  • 7. 7 Explanations in Recommender SystemExplanations in Recommender System Now let’s talk about Explanations:  Important pieces of information that are used by both selling and buying agents to increase their performance.  Another definition … it is a description that makes users better realize if the recommended item is relevant to their needs or not.
  • 8. 8 YouTube Explanation System A Restaurant Recommendation Explanation Explanations - ExamplesExplanations - Examples
  • 9. 9 Amazon Explanation System Explanations - ExampleExplanations - Example
  • 10. 10 Why Using Explanations in RSWhy Using Explanations in RS??
  • 11. 11  More on this artist …  Try something from similar artists …  Someone similar to you also like this …  As you listened to that, you may want this …  These two go together …  This is highly rated …  Try something new …  Similar or related products …  Complementary accessories ...  Gift idea ...  Welcome back (recently viewed) …  For you today …  New for you …  Hot / Most popular of this type …  Other people also do this … Phrases Expressing ExplanationsPhrases Expressing Explanations
  • 12. 12
  • 13. 13 Information VisualizationInformation Visualization  Human eyes can interpret a graph much faster than plain texts, as it can process many visual cues simultaneously.  The design look of the website is what visitors care much about compared to other website features such as information structure, information focus and usefulness of information.  Visualization has been used in recommender systems in both offering recommendation to users and explaining why these recommendations were given.
  • 14. 14 Visualization TechniquesVisualization Techniques To visualize information, a number of visualization techniques have been used such as tables, images, diagrams, text-highlighting, color schemes, rating and animation. More sophisticated methods include: Geometrically-transformed displays include techniques such as scatterplot matrices, projection pursuit techniques, prosection views, hyperslice and parallel coordinates Iconic displays include little faces, needle icons, star icons, stick figure icons, color icons and TileBars. Dense pixel displays include techniques such as recursive patterns and circle segments Stacked displays include dimensional stacking.
  • 15. In Amazon’s website, there is the use of techniques such as text-highlighting, five-star rating scales, images, colors, text size, tables, animation… 15 Example #1:Example #1:
  • 16. 16 a ten-star rating scale: The IMDb.com system uses Example #2:Example #2:
  • 17. An example for using different visualization techniques in some explanations interface 17 Example #3:Example #3:
  • 18. However, information visualization suffers from the following common problems:  Clutter  Data overload  Size of the graph  Time complexity 18 Visualization ProblemsVisualization Problems
  • 19. 19 Correlated DisciplinesCorrelated Disciplines A. Decision Making  Decision making is the selection of a course of action from two or more alternatives in order to solve a problem or to achieve an objective.  It was found that the format of the information presented can affect what decisions consumers can make.  The integration of recommendation technologies with a profound realization of human decision making can improve the quality of recommendation for users and the predictability of decision outcomes. There is strong a relationship between visualization of information and two other disciplines. Understanding this relationship is important for a better RS design:
  • 20. B. Human Computer Interaction  Human Computer Interaction (HCI) is concerned with how people interact with computers and how computers can be developed for successful interaction with human beings.  The goal of HCI is to design systems that minimize the barrier between the human's cognitive model of what they want to accomplish and the computer's understanding of the user's task.  By designing a good explanation interface, we can better explain recommendations and can even push users to make further requests. 20 Correlated DisciplinesCorrelated Disciplines
  • 21. 21 There are a number of future research directions we would like to explore. For example: Future DirectionsFuture Directions