SlideShare una empresa de Scribd logo
1 de 45
FACULTEIT WETENSCHAPPEN

Visualisatie van
muziekaanbevelingen
Een visueel uitlegsysteem voor collaboratieve filtering

Joris SCHELFAUT
Promotor:
Prof. Dr. Ir. E. Duval, Prof. Dr. K. Verbert, Dr. J. Klerkx
Begeleider:
Prof. Dr. K. Verbert, Dr. J. Klerkx

Academiejaar 2012-2013
FACULTEIT WETENSCHAPPEN

Recommender system
• Compute personalized item suggestions based
on the user’s interaction with the system
– Listening history
– Items ratings
– Item purchases
–…

• Last.fm, Netflix, IMDb, Facebook, Amazon, …
FACULTEIT WETENSCHAPPEN

Recommender system
• Database (items / users)
FACULTEIT WETENSCHAPPEN

Recommender system
• Database

• Algorithms
FACULTEIT WETENSCHAPPEN

Recommender system > CBF
FACULTEIT WETENSCHAPPEN

Recommender system > CF
FACULTEIT WETENSCHAPPEN

Black box problem
FACULTEIT WETENSCHAPPEN

Explanation system
FACULTEIT WETENSCHAPPEN

Explanation system > Examples
FACULTEIT WETENSCHAPPEN

Explanation system > evaluation
FACULTEIT WETENSCHAPPEN

Explanation system > evaluation
FACULTEIT WETENSCHAPPEN

Objective
• Make a visualization
...that can explain music suggestions
• Interactive
• Steer the process (if possible)
• Evaluation based on previously described aims
• Non-professional users (learnability)
FACULTEIT WETENSCHAPPEN








Target audience
Visualization design
Implementation
Evaluation results
Conclusion
Demo
FACULTEIT WETENSCHAPPEN

Target audience
FACULTEIT WETENSCHAPPEN

Visualization design
FACULTEIT WETENSCHAPPEN

Visualization design
FACULTEIT WETENSCHAPPEN

Visualization design
FACULTEIT WETENSCHAPPEN

Implementation > Recommender
• Last.fm
– Collaborative approach
– Lots of data
– Active users

• Last.fm API
– Listening history
– Neighbours
– Recommendations
FACULTEIT WETENSCHAPPEN

Implementation > Application
• Chrome extension
– Inject HTML into a webpage
FACULTEIT WETENSCHAPPEN

Implementation > Visualization
• D3.js
– Lots of existing code
– Well documented
– Works in almost all
modern browsers
FACULTEIT WETENSCHAPPEN

Evaluation > Iteration 1
FACULTEIT WETENSCHAPPEN

Evaluation > Iteration 1
FACULTEIT WETENSCHAPPEN

Evaluation > Iteration 1
FACULTEIT WETENSCHAPPEN

Evaluation > Iteration 1
• Feasable?
– Insight
– Usability

• Think aloud / SUS
• 5 Test users
FACULTEIT WETENSCHAPPEN

Evaluation > Iteration 1
• Feasable?
– Yes
– Rationale could be
discovered

• SUS avg: 77
FACULTEIT WETENSCHAPPEN

Evaluation > Iteration 2
FACULTEIT WETENSCHAPPEN

Evaluation > Iteration 2
• Is the transformation from paper to digital
successful?
– Insight
– Usability

• 5 test users
• Think aloud / SUS
FACULTEIT WETENSCHAPPEN

Evaluation > Iteration 2
• Is the transformation from paper to digital
successful?
– Yes

• Issue: parallel edges are hard to distinguish
• SUS avg: 79.5
FACULTEIT WETENSCHAPPEN

Evaluation > Iteration 3
FACULTEIT WETENSCHAPPEN

Evaluation > Iteration 3
• Real data
– Insight: more relevant
data

• Focus on usability
– Option menu

• Insight
• 5 test users
• Think aloud / SUS
FACULTEIT WETENSCHAPPEN

Evaluation > Iteration 3
• Negative:
– Threshold
– Slow loading times
– Distinguish between recommendations and
owned items
– Learning

• SUS avg: 76.5
FACULTEIT WETENSCHAPPEN

Evaluation > Iteration 4
FACULTEIT WETENSCHAPPEN

Evaluation > Iteration 4
FACULTEIT WETENSCHAPPEN

Evaluation > Iteration 4
•
•
•
•

Where changes positive?
Evaluating aims
10 test users
Think aloud / SUS
FACULTEIT WETENSCHAPPEN

Evaluation > Iteration 4
• Positive:
– Tension
– Underlining owned items
– Keeping current data in local storage

• Negative
– Learning
– Visual clutter when a showing approx. 40+ items
FACULTEIT WETENSCHAPPEN

Evaluation > Iteration 4
• SUS avg 80.5
FACULTEIT WETENSCHAPPEN

Evaluation > Iteration 4
•
•
•
•
•
•
•

Transparency: yes.
Scrutability: no.
Trust: sometimes.
Effectiveness: sometimes.
Persuasiveness: sometimes.
Efficiency: yes.
Satisfaction: yes.
FACULTEIT WETENSCHAPPEN

Conclusion > Objectives
•
•
•
•

Varying levels of perceived usefulness
SUS score of 80.5 for iteration 4
Learnability can improve
Design can be effective for explaining
collaborative recommendations
• Starting point for further exploration
FACULTEIT WETENSCHAPPEN

Conclusion > Future work
• Visualization
–
–
–
–

Use symmetry in data to retain users instead of artists as nodes
Additional interactions (e.g. edges)
Clutter reduction through opacity
Temporary hide users

• Data
– Improve data load times through caching

• Learnability
– Further improve labels and visual clues

• Evaluation
– Benchmarks, expert-based, heuristic
FACULTEIT WETENSCHAPPEN

Demo
• https://chrome.google.com/webstore/detail/s
oundsuggest/jimmblcjmmjjfaklclmohcnabndli
dmb?hl=nl&gl=BE
• http://www.last.fm/home/recs
FACULTEIT WETENSCHAPPEN

Stats
FACULTEIT WETENSCHAPPEN

Stats
FACULTEIT WETENSCHAPPEN

Stats
FACULTEIT WETENSCHAPPEN

Thank you!
• For your attention!
• Special thanks to my supervisors Joris and
Katrien!
FACULTEIT WETENSCHAPPEN

Questions?

Más contenido relacionado

Destacado

Destacado (19)

numerical analysis
numerical analysisnumerical analysis
numerical analysis
 
Modeling the water-energy-food nexus in the Indus River of Pakistan
Modeling the water-energy-food nexus in the Indus River of PakistanModeling the water-energy-food nexus in the Indus River of Pakistan
Modeling the water-energy-food nexus in the Indus River of Pakistan
 
Behavioral Economics and the Design of Agricultural Index Insurance in Develo...
Behavioral Economics and the Design of Agricultural Index Insurance in Develo...Behavioral Economics and the Design of Agricultural Index Insurance in Develo...
Behavioral Economics and the Design of Agricultural Index Insurance in Develo...
 
CEU lecture 6
CEU lecture 6CEU lecture 6
CEU lecture 6
 
CEU lecture 3 2016
CEU lecture 3 2016CEU lecture 3 2016
CEU lecture 3 2016
 
Agricultural Economics Mid Term Progress Submission
Agricultural Economics Mid Term Progress SubmissionAgricultural Economics Mid Term Progress Submission
Agricultural Economics Mid Term Progress Submission
 
Ceu lecture 4
Ceu lecture 4Ceu lecture 4
Ceu lecture 4
 
PHP6 and HTML5
PHP6 and HTML5PHP6 and HTML5
PHP6 and HTML5
 
Agricultural Productivity and Economic Development in Southern Africa
Agricultural Productivity and Economic Development in Southern AfricaAgricultural Productivity and Economic Development in Southern Africa
Agricultural Productivity and Economic Development in Southern Africa
 
Modeling the water food-energy nexus in the arab world: River basin modeling ...
Modeling the water food-energy nexus in the arab world: River basin modeling ...Modeling the water food-energy nexus in the arab world: River basin modeling ...
Modeling the water food-energy nexus in the arab world: River basin modeling ...
 
Selecting A Content Management System For Athabasca University
Selecting A Content Management System For Athabasca UniversitySelecting A Content Management System For Athabasca University
Selecting A Content Management System For Athabasca University
 
Selecting a content management system
Selecting a content management systemSelecting a content management system
Selecting a content management system
 
CEU lecture 2 2016
CEU lecture 2 2016CEU lecture 2 2016
CEU lecture 2 2016
 
Plataformas educativas
Plataformas educativasPlataformas educativas
Plataformas educativas
 
[Ronald p. morash] bridge to abstract mathematics
[Ronald p. morash] bridge to abstract mathematics[Ronald p. morash] bridge to abstract mathematics
[Ronald p. morash] bridge to abstract mathematics
 
Proof in Mathematics
Proof in MathematicsProof in Mathematics
Proof in Mathematics
 
Image processing (Signal Processing)
Image processing (Signal Processing)Image processing (Signal Processing)
Image processing (Signal Processing)
 
An Agricultural Economics Research Agenda in Ethiopia – Some Reflections
An Agricultural Economics Research Agenda in Ethiopia – Some ReflectionsAn Agricultural Economics Research Agenda in Ethiopia – Some Reflections
An Agricultural Economics Research Agenda in Ethiopia – Some Reflections
 
Solving Equations
Solving EquationsSolving Equations
Solving Equations
 

Último

Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Safe Software
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
panagenda
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
Joaquim Jorge
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
?#DUbAI#??##{{(☎️+971_581248768%)**%*]'#abortion pills for sale in dubai@
 

Último (20)

Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 

Visualization of Music Suggestions

Notas del editor

  1. Hi, my name is JorisSchelfaut, I’m an Applied Informatics student and my thesis subject is “Visualization of music suggestions”.
  2. In this presentation we will look at recommender systems; these are systems that compute personalized item suggestions based on the user’s interaction with the system, for example by tracking listening history in the case of music recommendation, or ratings given to particular articles in an item catalog. Examples of these systems are Last.fm (music), IMDb (movies), Netflix (movies), Amazon (books), et cetera.
  3. Suppose you’re collecting all kinds of geometric objects, and we have a database full of cubes, cones, spheres et cetera. We have a number of users that have rated these objects. Next we also have one or more algorithms to mine suggestions from the data.
  4. Algorithms to compute these suggestions are for example content-based approaches that use similarity between items to compute a suggestion. For example, in our database rectangles are fairly similar to cubes. So if someone who has rated a rectangle as “amazing”, the system can then suggest a cube to that particular user.
  5. Another approach would be to use similarity between user profiles to classify users into some kind of cluster. For example if two people love cones and pyramids, we’ll assume these users are very similar, i.e., they’re neighbors. If one of these users happens to love cylinders as well, the system might think “aha, the other person might like this as well, let’s recommend this item to that user”. This approach is called collaborative filtering.
  6. One problem that is associated with recommender systems is that the suggestions that they compute are often presented in a way that the user doesn’t have an idea how the suggestion was computed. For example our friend Billy the sphere collector receives a recommendation for a parallelepiped, and thinks “Are you kidding me?”, while there might be a perfectly reasonable explanation why this would be an interesting recommendation. Billy looses trust in the recommender system and goes looking elsewhere for cool volumes.
  7. To solve this problem of decreased levels of trust and acceptance of recommendations, we could try to explain the reasoning behind the suggestions. What we aim for is some level of insight into the recommendation rationale. This is not a trivial task: the system may to too complex to explain efficiently, or revealing too much information on the algorithm may is not what developers want, as significant research efforts were spent to create it.
  8. One way of providing insight is by creating some kind of explanation system. For example the recommendation process can be visualized, which also brings us to the second part of the title of this thesis: “visualization of music suggestions”. A number of such systems exist (see slides).
  9. These systems can be evaluated based on a number of “aims” (see table):Transparency: Explain how the system works.Scrutability: Allow users to tell the system is wrong.Trust: Increase users' confidence in the system.Effectiveness: Help users make good decisions.Persuasiveness: Convince users to try or buy.Efficiency: Help users make decisions faster.Satisfaction: Increase the ease of usability or enjoyment.
  10. Make a visualization that can explain music suggestions, and that is interactive and enables the user to steer the process (if possible). Evaluation based on previously described aims
  11. Now that we have an understanding of the big picture of the problem and context, we will give an overview of the remainder of the presentation.First we will take a closer look at the target audienceNext we will describe the design of the visualizationThen we will present how this was implementedNext we will give an overview of the most important test resultsFinally a conclusion is presented.
  12. The target audience is largely based on the so-called savants and enthusiasts (see table on slide). (Note that the last category is the predominant one in the population. I have to say I found that result a bit remarkable based on studies showing a close relationship between music and emotion)
  13. In the visualization, the items (or artists in this case) of the user are laid out in a circle.
  14. For each pair of items that the user owns, an edge is drawn between the nodes, creating a fully connected sub-graph. By highlighting a user, the corresponding items and edges will be highlighted as well, and vice versa.
  15. In an effort to reduce visual clutter and make the visualization more visually pleasing, edge-bundling is applied to the edges so that the edges are drawn to each other.
  16. To test the visualization we tried to explain Last.fm’s collaborative-based recommender
  17. The visualization was injected into the recommendations page using a chrome browser extension.
  18. The extension collects data the Last.fm API and transforms it into a visualization that is built with D3.js, a JavaScript library to create vector graphics in HTML.
  19. The development took place in a number of iterations to gradually improve the application. In the first iteration we used a paper prototype. Here we wanted mainly to find out if the visualization had any potential.
  20. Selecting a user