SlideShare une entreprise Scribd logo
1  sur  24
Télécharger pour lire hors ligne
Can Trailers Help to
Alleviate Popularity Bias in
Choice-Based Preference
Elicitation?
Mark P. Graus
Martijn C. Willemsen
Human-Technology
Interaction Group
Eindhoven University
of Technology
Summary
• We wanted to see if we could make people chose
less popular items in a choice-based preference
elicitation recommender system by showing them
trailers.
• We tested this in a between subjects user study.
• We found that after watching trailers people chose
less popular items, while user experience was not
negatively affected.
9/16/2016
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
2
Motivation
9/16/2016
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
3
Latent Feature Diversification
• Can we reduce choice overload
through diversification based on
the latent features of a matrix
factorization model?
Willemsen, M. C., Graus, M. P., & Knijnenburg, B.
P. (2016). Understanding the role of latent feature
diversification on choice difficulty and satisfaction.
User Modeling and User-Adapted Interaction, 1–
43. http://doi.org/10.1007/s11257-016-9178-6
Latent Feature 1
LatentFeature2
9/16/2016
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
4
Latent Feature Diversification Findings
9/16/2016
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
5
0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
low mid high
standardizedscore
diversification
Perceived diversity
-1
-0.8
-0.6
-0.4
-0.2
0
0.2
low mid high
standardizedscore
diversification
Expected choice difficulty
LatentFeature2
Latent Feature 1
4) Iteration 2
Choice-Based Preference Elicitation
• Can we improve the user experience
during cold start by having people
choose between items instead of
rating items?
Graus, M. P., & Willemsen, M. C. (2015). Improving the
User Experience during Cold Start through Choice-
Based Preference Elicitation. In Proceedings of the 9th
ACM Conference on Recommender Systems - RecSys
’15 (pp. 273–276). New York, New York, USA: ACM
Press. http://doi.org/10.1145/2792838.2799681
9/16/2016
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
6
How does this work? Step 1
Latent Feature 1
LatentFeature2
Iteration 1a: Diversified choice set is
calculated from a matrix factorization
model (red items)
Iteration 1b: User vector (blue arrow) is moved
towards chosen item (green item), items with
lowest predicted rating are discarded (greyed
out items)
9/16/2016
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
7
How does this work? Step 2
Iteration 2: New diversified choice set
(blue items)
End of Iteration 2: with updated vector and
more items discarded based on second choice
(green item)
9/16/2016
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
8
Choice-Based Preference Elicitation
Findings
• People are more satisfied with choice-based than
rating-based interfaces
• This comes mainly because of increased popularity
(items with many ratings)
But we do not want to
recommend popular
items!
9/16/2016
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
9
Satisfaction
with Chosen
Item
Popularity
Difficulty
Intra List
Similarity
-2.407(.381)
p<.001
-.240 (.145)
p<.1
-.479 (.111)
p<.001
-.257 (.045)
p<.001
14.00 (4.51)
p<.01
Choice-
Based List
+
+
- -
+
Why do people end up with popular
items?
• Our hypothesis
• Users don’t know all movies, hard to judge based on
metadata alone
• People choose movies they know
• People know movies that are popular
• Choosing popular movies results in popular recommendations
• Our Solution
• Provide trailers as additional information for making choices
9/16/2016
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
10
Rationale
• In the music domain
• Implicit Feedback
• Movie domain
• Implicit feedback is sparse
• I (can) listen to 100s of tracks in a week, but I can’t
watch 100s of movies a week (and sustain my job).
• We can approximate experiencing movies by
providing trailers
9/16/2016
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
11
Study
9/16/2016
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
12
Choice-Based Interface with or without
Trailers
• N = 71
9/16/2016
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
13
Expected Effects
Trailers
Perceived
Diversity
Informativeness
Perceived
Novelty
Choice
Satisfaction
System
Satisfaction
Popularity of
Chosen Items
- +
+
+?
-?-
-
+
9/16/2016
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
14
Set Up
• Random assignment
• Choice Based Preference Elicitation – 9 choices of 10 items
[with/without trailers]
• Recommendation List – Top-10 Items [with/without trailers]
• Survey to measure User Experience
• Informativeness
• Perceived Diversity
• Perceived Novelty
• System Satisfaction
• Choice Satisfaction
9/16/2016
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
15
Results
9/16/2016
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
16
Do trailers affect the popularity of chosen
items?
• Checked through repeated measures (10 choices)
• Popularity is expressed as the rank ordering by
number of ratings in MovieLens dataset
• Trailers do not decrease popularity of choices
• The popularity rank of the item chosen in each choice
set
• The average popularity rank of all items in each choice
set
9/16/2016
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
17
However: Relative Popularity of Choice
• average popularity rank of choice set – popularity
rank of chosen item
9/16/2016
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
18
If we look at people that actually watched
trailers
• People that watch trailers are
more likely to pick less popular
movies from the lists
9/16/2016
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
19
User Experience
Choice
Satisfaction
Perceived
Diversity
System
Satisfaction
Informativeness
.570 (.295)
p < 0.1
-.604 (.091)
p < 0.01
.244 (.162)
n.s.
.785 (.115)
p < 0.01
-.266 (.122)
p < 0.05
Trailers
.611 (.256)
p < 0.05
-.570 (.259)
p < 0.05
-
+
-
-
+
9/16/2016
+
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
20
Conclusions
9/16/2016
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
21
What we found
• Providing people with trailers does make them
choose less popular items.
• No indication that the overall satisfaction is affected
negatively or positively
• As opposed to initial study where popularity resulted in
increased satisfaction
9/16/2016
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
22
Limitations
• When were trailers watched?
• In the preference elicitation task?
• In the decision task?
Future Work
• How do trailers affect a more standard rating
interface?
9/16/2016
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
23
Thank You
• Questions/remarks?
Mark Graus – PhD Student
Human-Technology Interaction Group
Eindhoven University of Technology
m.p.graus@tue.nl
https://twitter.com/newmarrk
https://linkedin.com/in/markgraus
http://www.marrk.nl
9/16/2016
Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @
RecSys '16
24

Contenu connexe

En vedette

8 B2B Marketing Trends for 2013 from hawkeye
8 B2B Marketing Trends for 2013 from hawkeye8 B2B Marketing Trends for 2013 from hawkeye
8 B2B Marketing Trends for 2013 from hawkeye
John Tedstrom
 
Building A Machine Learning Platform At Quora (1)
Building A Machine Learning Platform At Quora (1)Building A Machine Learning Platform At Quora (1)
Building A Machine Learning Platform At Quora (1)
Nikhil Garg
 

En vedette (12)

Introduction to Linux
Introduction to LinuxIntroduction to Linux
Introduction to Linux
 
8 B2B Marketing Trends for 2013 from hawkeye
8 B2B Marketing Trends for 2013 from hawkeye8 B2B Marketing Trends for 2013 from hawkeye
8 B2B Marketing Trends for 2013 from hawkeye
 
WP or Drupal (or both): A Framework for Client CMS Decisions
WP or Drupal (or both): A Framework for Client CMS Decisions WP or Drupal (or both): A Framework for Client CMS Decisions
WP or Drupal (or both): A Framework for Client CMS Decisions
 
Recsys 2016: Modeling Contextual Information in Session-Aware Recommender Sys...
Recsys 2016: Modeling Contextual Information in Session-Aware Recommender Sys...Recsys 2016: Modeling Contextual Information in Session-Aware Recommender Sys...
Recsys 2016: Modeling Contextual Information in Session-Aware Recommender Sys...
 
Building enterprise applications on the cloud (Level 100)
Building enterprise applications on the cloud (Level 100)Building enterprise applications on the cloud (Level 100)
Building enterprise applications on the cloud (Level 100)
 
[EMPIRE 2016] Adapt to Emotional Reactions In Context-aware Personalization
[EMPIRE 2016] Adapt to Emotional Reactions In Context-aware Personalization[EMPIRE 2016] Adapt to Emotional Reactions In Context-aware Personalization
[EMPIRE 2016] Adapt to Emotional Reactions In Context-aware Personalization
 
Intelligently matching users to questions for reading and writing
Intelligently matching users to questions for reading and writingIntelligently matching users to questions for reading and writing
Intelligently matching users to questions for reading and writing
 
Teads Entertainment Barometer October 2015
Teads Entertainment Barometer October 2015Teads Entertainment Barometer October 2015
Teads Entertainment Barometer October 2015
 
What Is A CTP?
What Is A CTP?What Is A CTP?
What Is A CTP?
 
The Road to become a Social Media Influencer
The Road to become a Social Media InfluencerThe Road to become a Social Media Influencer
The Road to become a Social Media Influencer
 
RecSys 2016 Talk: Feature Selection For Human Recommenders
RecSys 2016 Talk: Feature Selection For Human RecommendersRecSys 2016 Talk: Feature Selection For Human Recommenders
RecSys 2016 Talk: Feature Selection For Human Recommenders
 
Building A Machine Learning Platform At Quora (1)
Building A Machine Learning Platform At Quora (1)Building A Machine Learning Platform At Quora (1)
Building A Machine Learning Platform At Quora (1)
 

Dernier

Module for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learningModule for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learning
levieagacer
 
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Sérgio Sacani
 
Digital Dentistry.Digital Dentistryvv.pptx
Digital Dentistry.Digital Dentistryvv.pptxDigital Dentistry.Digital Dentistryvv.pptx
Digital Dentistry.Digital Dentistryvv.pptx
MohamedFarag457087
 
The Mariana Trench remarkable geological features on Earth.pptx
The Mariana Trench remarkable geological features on Earth.pptxThe Mariana Trench remarkable geological features on Earth.pptx
The Mariana Trench remarkable geological features on Earth.pptx
seri bangash
 
Human genetics..........................pptx
Human genetics..........................pptxHuman genetics..........................pptx
Human genetics..........................pptx
Silpa
 

Dernier (20)

Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....
Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....
Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....
 
Exploring Criminology and Criminal Behaviour.pdf
Exploring Criminology and Criminal Behaviour.pdfExploring Criminology and Criminal Behaviour.pdf
Exploring Criminology and Criminal Behaviour.pdf
 
Bhiwandi Bhiwandi ❤CALL GIRL 7870993772 ❤CALL GIRLS ESCORT SERVICE In Bhiwan...
Bhiwandi Bhiwandi ❤CALL GIRL 7870993772 ❤CALL GIRLS  ESCORT SERVICE In Bhiwan...Bhiwandi Bhiwandi ❤CALL GIRL 7870993772 ❤CALL GIRLS  ESCORT SERVICE In Bhiwan...
Bhiwandi Bhiwandi ❤CALL GIRL 7870993772 ❤CALL GIRLS ESCORT SERVICE In Bhiwan...
 
Module for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learningModule for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learning
 
FAIRSpectra - Enabling the FAIRification of Spectroscopy and Spectrometry
FAIRSpectra - Enabling the FAIRification of Spectroscopy and SpectrometryFAIRSpectra - Enabling the FAIRification of Spectroscopy and Spectrometry
FAIRSpectra - Enabling the FAIRification of Spectroscopy and Spectrometry
 
Climate Change Impacts on Terrestrial and Aquatic Ecosystems.pptx
Climate Change Impacts on Terrestrial and Aquatic Ecosystems.pptxClimate Change Impacts on Terrestrial and Aquatic Ecosystems.pptx
Climate Change Impacts on Terrestrial and Aquatic Ecosystems.pptx
 
Locating and isolating a gene, FISH, GISH, Chromosome walking and jumping, te...
Locating and isolating a gene, FISH, GISH, Chromosome walking and jumping, te...Locating and isolating a gene, FISH, GISH, Chromosome walking and jumping, te...
Locating and isolating a gene, FISH, GISH, Chromosome walking and jumping, te...
 
GBSN - Microbiology (Unit 3)
GBSN - Microbiology (Unit 3)GBSN - Microbiology (Unit 3)
GBSN - Microbiology (Unit 3)
 
Chemistry 5th semester paper 1st Notes.pdf
Chemistry 5th semester paper 1st Notes.pdfChemistry 5th semester paper 1st Notes.pdf
Chemistry 5th semester paper 1st Notes.pdf
 
Grade 7 - Lesson 1 - Microscope and Its Functions
Grade 7 - Lesson 1 - Microscope and Its FunctionsGrade 7 - Lesson 1 - Microscope and Its Functions
Grade 7 - Lesson 1 - Microscope and Its Functions
 
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
 
GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)
 
Site Acceptance Test .
Site Acceptance Test                    .Site Acceptance Test                    .
Site Acceptance Test .
 
300003-World Science Day For Peace And Development.pptx
300003-World Science Day For Peace And Development.pptx300003-World Science Day For Peace And Development.pptx
300003-World Science Day For Peace And Development.pptx
 
Digital Dentistry.Digital Dentistryvv.pptx
Digital Dentistry.Digital Dentistryvv.pptxDigital Dentistry.Digital Dentistryvv.pptx
Digital Dentistry.Digital Dentistryvv.pptx
 
GBSN - Microbiology (Unit 1)
GBSN - Microbiology (Unit 1)GBSN - Microbiology (Unit 1)
GBSN - Microbiology (Unit 1)
 
The Mariana Trench remarkable geological features on Earth.pptx
The Mariana Trench remarkable geological features on Earth.pptxThe Mariana Trench remarkable geological features on Earth.pptx
The Mariana Trench remarkable geological features on Earth.pptx
 
Human genetics..........................pptx
Human genetics..........................pptxHuman genetics..........................pptx
Human genetics..........................pptx
 
Introduction of DNA analysis in Forensic's .pptx
Introduction of DNA analysis in Forensic's .pptxIntroduction of DNA analysis in Forensic's .pptx
Introduction of DNA analysis in Forensic's .pptx
 
Proteomics: types, protein profiling steps etc.
Proteomics: types, protein profiling steps etc.Proteomics: types, protein profiling steps etc.
Proteomics: types, protein profiling steps etc.
 

Can Trailers Help to Alleviate Popularity Bias in Choice-Based Preference Elicitation?

  • 1. Can Trailers Help to Alleviate Popularity Bias in Choice-Based Preference Elicitation? Mark P. Graus Martijn C. Willemsen Human-Technology Interaction Group Eindhoven University of Technology
  • 2. Summary • We wanted to see if we could make people chose less popular items in a choice-based preference elicitation recommender system by showing them trailers. • We tested this in a between subjects user study. • We found that after watching trailers people chose less popular items, while user experience was not negatively affected. 9/16/2016 Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 2
  • 3. Motivation 9/16/2016 Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 3
  • 4. Latent Feature Diversification • Can we reduce choice overload through diversification based on the latent features of a matrix factorization model? Willemsen, M. C., Graus, M. P., & Knijnenburg, B. P. (2016). Understanding the role of latent feature diversification on choice difficulty and satisfaction. User Modeling and User-Adapted Interaction, 1– 43. http://doi.org/10.1007/s11257-016-9178-6 Latent Feature 1 LatentFeature2 9/16/2016 Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 4
  • 5. Latent Feature Diversification Findings 9/16/2016 Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 5 0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 low mid high standardizedscore diversification Perceived diversity -1 -0.8 -0.6 -0.4 -0.2 0 0.2 low mid high standardizedscore diversification Expected choice difficulty
  • 6. LatentFeature2 Latent Feature 1 4) Iteration 2 Choice-Based Preference Elicitation • Can we improve the user experience during cold start by having people choose between items instead of rating items? Graus, M. P., & Willemsen, M. C. (2015). Improving the User Experience during Cold Start through Choice- Based Preference Elicitation. In Proceedings of the 9th ACM Conference on Recommender Systems - RecSys ’15 (pp. 273–276). New York, New York, USA: ACM Press. http://doi.org/10.1145/2792838.2799681 9/16/2016 Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 6
  • 7. How does this work? Step 1 Latent Feature 1 LatentFeature2 Iteration 1a: Diversified choice set is calculated from a matrix factorization model (red items) Iteration 1b: User vector (blue arrow) is moved towards chosen item (green item), items with lowest predicted rating are discarded (greyed out items) 9/16/2016 Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 7
  • 8. How does this work? Step 2 Iteration 2: New diversified choice set (blue items) End of Iteration 2: with updated vector and more items discarded based on second choice (green item) 9/16/2016 Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 8
  • 9. Choice-Based Preference Elicitation Findings • People are more satisfied with choice-based than rating-based interfaces • This comes mainly because of increased popularity (items with many ratings) But we do not want to recommend popular items! 9/16/2016 Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 9 Satisfaction with Chosen Item Popularity Difficulty Intra List Similarity -2.407(.381) p<.001 -.240 (.145) p<.1 -.479 (.111) p<.001 -.257 (.045) p<.001 14.00 (4.51) p<.01 Choice- Based List + + - - +
  • 10. Why do people end up with popular items? • Our hypothesis • Users don’t know all movies, hard to judge based on metadata alone • People choose movies they know • People know movies that are popular • Choosing popular movies results in popular recommendations • Our Solution • Provide trailers as additional information for making choices 9/16/2016 Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 10
  • 11. Rationale • In the music domain • Implicit Feedback • Movie domain • Implicit feedback is sparse • I (can) listen to 100s of tracks in a week, but I can’t watch 100s of movies a week (and sustain my job). • We can approximate experiencing movies by providing trailers 9/16/2016 Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 11
  • 12. Study 9/16/2016 Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 12
  • 13. Choice-Based Interface with or without Trailers • N = 71 9/16/2016 Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 13
  • 14. Expected Effects Trailers Perceived Diversity Informativeness Perceived Novelty Choice Satisfaction System Satisfaction Popularity of Chosen Items - + + +? -?- - + 9/16/2016 Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 14
  • 15. Set Up • Random assignment • Choice Based Preference Elicitation – 9 choices of 10 items [with/without trailers] • Recommendation List – Top-10 Items [with/without trailers] • Survey to measure User Experience • Informativeness • Perceived Diversity • Perceived Novelty • System Satisfaction • Choice Satisfaction 9/16/2016 Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 15
  • 16. Results 9/16/2016 Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 16
  • 17. Do trailers affect the popularity of chosen items? • Checked through repeated measures (10 choices) • Popularity is expressed as the rank ordering by number of ratings in MovieLens dataset • Trailers do not decrease popularity of choices • The popularity rank of the item chosen in each choice set • The average popularity rank of all items in each choice set 9/16/2016 Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 17
  • 18. However: Relative Popularity of Choice • average popularity rank of choice set – popularity rank of chosen item 9/16/2016 Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 18
  • 19. If we look at people that actually watched trailers • People that watch trailers are more likely to pick less popular movies from the lists 9/16/2016 Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 19
  • 20. User Experience Choice Satisfaction Perceived Diversity System Satisfaction Informativeness .570 (.295) p < 0.1 -.604 (.091) p < 0.01 .244 (.162) n.s. .785 (.115) p < 0.01 -.266 (.122) p < 0.05 Trailers .611 (.256) p < 0.05 -.570 (.259) p < 0.05 - + - - + 9/16/2016 + Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 20
  • 21. Conclusions 9/16/2016 Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 21
  • 22. What we found • Providing people with trailers does make them choose less popular items. • No indication that the overall satisfaction is affected negatively or positively • As opposed to initial study where popularity resulted in increased satisfaction 9/16/2016 Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 22
  • 23. Limitations • When were trailers watched? • In the preference elicitation task? • In the decision task? Future Work • How do trailers affect a more standard rating interface? 9/16/2016 Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 23
  • 24. Thank You • Questions/remarks? Mark Graus – PhD Student Human-Technology Interaction Group Eindhoven University of Technology m.p.graus@tue.nl https://twitter.com/newmarrk https://linkedin.com/in/markgraus http://www.marrk.nl 9/16/2016 Graus, Willemsen: Can Trailers Help to Alleviate ... IntRS @ RecSys '16 24