SlideShare una empresa de Scribd logo
1 de 58
Descargar para leer sin conexión
The Effect of Explanations and Algorithmic Accuracy
on
Visual Recommender Systems of Artistic Images
Pontificia UniversidadCatólica de Chile (PUC Chile)
Vicente
Domínguez
Pablo
Messina
Ivania
Donoso-Guzmán
Denis
Parra
The Effect of Explanations and Algorithmic Accuracy
on
Visual Recommender Systems of Artistic Images
(candidate to best paper)
Pontificia UniversidadCatólica de Chile (PUC Chile)
Vicente
Domínguez
Pablo
Messina
Ivania
Donoso-Guzmán
Denis
Parra
The Online Artwork Market
• Online artwork market: Growing since 2008,
despite global crises!
• In 2011, art received $11.57 billion in total global
annual revenue, over $2 billion versus 2010
(*forbes)
• Recommender systems could play an important
role, just like in other e-commerce industries.
[forbes] https://www.forbes.com/sites/abigailesman/2012/02/29/ the- worlds- strongest- economy- the- global- art- market/ (2012)
March 17th 2019 Dominguez et al ~ ACM IUI 2019 3
Related Work: Art Recommendation
March 17th 2019 Dominguez et al ~ ACM IUI 2019 4
• Previous art recommendationprojects date for as long as 2007, such
as the CHIP project to recommend paintings from Rijksmuseum.
(Aroyo et al., 2007)
• Some approaches have used:
– Ratings (Aroyo et al., 2007),
– Tags, Keywords or other textual features (Semeraro et al. 2012)
– Traditional visual features (van den Broek et al., 2006)
• Deep Learning (DL) have revolutionized visual feature learning, but few
works use them for recommending art (Het et al. 2016,Messina et al.
2018)
Related Work: Art Recommendation
March 17th 2019 Dominguez et al ~ ACM IUI 2019 5
• Previous art recommendationprojects date for as long as 2007, such
as the CHIP project to recommend paintings from Rijksmuseum.
(Aroyo et al., 2007)
• Some approaches have used:
– Ratings (Aroyo et al., 2007),
– Tags, Keywords or other textual features (Semeraro et al. 2012)
– Traditional visual features (van den Broek et al., 2006)
• Deep Learning (DL) have revolutionized visual feature learning, but few
works use them for recommending art (Het et al. 2016,Messina et al.
2018)
Related Work: Art Recommendation
• Previous art recommendationprojects date for as long as 2007, such
as the CHIP project to recommend paintings from Rijksmuseum.
(Aroyo et al., 2007)
• Some approaches have used:
– Ratings (Aroyo et al., 2007),
– Tags, Keywords or other textual features (Semeraro et al. 2012)
– Traditional visual features (van den Broek et al., 2006)
• Deep Learning (DL) have revolutionized computer vision, but few works
use DL methods for recommending art (He et al. 2016,Messina et al.
2018)
March 17th 2019 Dominguez et al ~ ACM IUI 2019 6
Our Approach to Image Recommendation
• Since 2017 we have been working on recommending art
images, using mostly content-based methods.
• Four papers published:
– ACM DLRS 2017: Dominguez,V.,Messina,P., Parra, D., Mery, D., Trattner,C., & Soto,A.
(2017,August).Comparing Neural and Attractivenessbased Visual Features forArtwork
Recommendation.In Proceedingsof the2nd Workshop on Deep Learning for
RecommenderSystems(pp.55-59).ACM.
– UMUAI 2018: Messina,P., Dominguez,V.,Parra, D., Trattner,C., & Soto, A. (2018).Content-
based artwork recommendation:integrating paintingmetadatawith neural and manually-
engineered visual features.UserModeling and User-Adapted Interaction,1-40.
– Two additional workshop papers in ACM RecSys 2018.
March 17th 2019 Dominguez et al ~ ACM IUI 2019 7
Open Questions from Content-Based RecSys
• We learned that visual features from DNNs perform better than
attractiveness visual features.
March 17th 2019 Dominguez et al ~ ACM IUI 2019 8
Average brightness
Saturation
Sharpness
Entropy
RGB-contrast
Colorfulness
Naturalness
Predictive Accuracy
Attractiveness
visual features
Deep Learning
visual features
Open Questions from Content-Based RecSys
• We learned that visual features from DNNs perform better than
attractiveness visual features, but they are harder to explain.
March 17th 2019 Dominguez et al ~ ACM IUI 2019 9
Predictive Accuracy
Explainability
Average brightness
Saturation
Sharpness
Entropy
RGB-contrast
Colorfulness
Naturalness
Attractiveness
visual features
Deep Learning
visual features
Explainability in Recommender Systems
• Explaining recommendations is a well-established and
active area of research, but there is little research on
explaining image recommendations.
March 17th 2019 Dominguez et al ~ ACM IUI 2019
Herlocker, J. L., Konstan, J. A., & Riedl, J. (2000).
Explaining collaborative filtering
recommendations. In Proceedings of the 2000
ACM conference on Computer supported
cooperative work (pp. 241-250)
10
Tintarev, N., & Masthoff, J. (2015). Explaining
recommendations: Design and evaluation.
In Recommender systems handbook (pp. 353-
382). Springer, Boston, MA.
Gaining Inspiration from DARPA XAI
March 17th 2019 Dominguez et al ~ ACM IUI 2019 11
DARPA XAI (Gunning, 2017)
Decision Tree
DNN
DARPA XAI inspiration
March 17th 2019 Dominguez et al ~ ACM IUI 2019 12
DARPA XAI (Gunning, 2017)
Decision Tree
DNN
Our research
AVF
DNN VF
Explainability Potential
PredictiveAccuracy
Is there an effect on
user perception if
we provide a UI with
explanations?
Our General Research Question
• Explainable &
Transparent UIs are well
perceived by users in
previous RecSys
research, but: Does it
matter to UX if you do
not produce accurate
enough predictions?
March 17th 2019 Dominguez et al ~ ACM IUI 2019 13
AVF
DNN VF
Explainability Potential
PredictiveAccuracy
- UI w/explanation
based on examples
- UI w/explanation
based on examples
or visual features
Research Questions
• RQ1. Given three different types of interfaces, one baseline interface without
explanations and two with explanations but different levels of transparency,
which one is perceived as most useful?
• RQ2. Furthermore, based on the visual content-based recommenderalgorithm
chosen (DNN or AVF), are there observable differences in how the three
interfaces are perceived?
• RQ3. How do independent variables such as algorithm, explainable interface
and domain knowledge interact in order to explain the user experience with the
recommender system in terms of perception of relevance, diversity,
explainabilityand user satisfaction?
March 17th 2019 Dominguez et al ~ ACM IUI 2019 14
Research Questions
• RQ1. Given three different types of interfaces, one baseline interface without
explanations and two with explanations but different levels of transparency,
which one is perceived as most useful?
• RQ2. Furthermore, based on the visual content-based recommenderalgorithm
chosen (DNN or AVF), are there observable differences in how the three
interfaces are perceived?
• RQ3. How do independent variables such as algorithm, explainable interface
and domain knowledge interact in order to explain the user experience with the
recommender system in terms of perception of relevance, diversity,
explainabilityand user satisfaction?
March 17th 2019 Dominguez et al ~ ACM IUI 2019 15
Research Questions
• RQ1. Given three different types of interfaces, one baseline interface without
explanations and two with explanations but different levels of transparency,
which one is perceived as most useful?
• RQ2. Furthermore, based on the visual content-based recommenderalgorithm
chosen (DNN or AVF), are there observable differences in how the three
interfaces are perceived?
• RQ3. How do independent variables such as algorithm, explainable interface
and domain knowledge interact in order to explain the user experience with the
recommender system in terms of perception of relevance, diversity,
explainabilityand user satisfaction?
March 17th 2019 Dominguez et al ~ ACM IUI 2019 16
Materials and Methodology
1. We collect image data from UGallery, an online store of
physical artworks (paintings and photographs).
2. We implement a system which records user preferences and
generates recommendations. Some of these
recommendations will have explanations.
3. We conduct a user study in Amazon Mechanical Turk to
assess the impact of algorithmic accuracy and explainable UI
on several user dimensions.
March 17th 2019 Dominguez et al ~ ACM IUI 2019 17
Data: UGallery
• Online Artwork
Store, based on CA,
USA.
• Mostly sales one-
of-a-kind physical
artwork.
March 17th 2019 Dominguez et al ~ ACM IUI 2019 18
CB RecSys algorithm: Visual Features
• (DNN) Deep Neural
Networks
• (AVF) Attractiveness-
based
March 17th 2019 Dominguez et al ~ ACM IUI 2019 19
Visual Features: DNN vs. AVF
• Deep Neural Networks (DNN):
we used an AlexNet DNN
(pre-trained with ImageNet
ILSVRC 2012 dataset)
(Krizhevsky et al, 2012)
• We map each artwork image
to its corresponding latent
vector of 4,096 dimensions
obtained at the fc6 layer of
the AlexNet network.
Visual Features: AVF
• Average brightness,
• Saturation,
• Sharpness,
• Entropy,
• RGB-contrast,
• Colorfulness,
• Naturalness
Jose San Pedro and Stefan Siersdorfer. 2009.
Ranking andClassifying Attractiveness of Photos
in Folksonomies.
In Proceedings of the 18thInternational
Conference on World Wide Web (WWW’09).
March 17th 2019 Dominguez et al ~ ACM IUI 2019 21
UGallery: Making Recommendations
• Scoring items based on cosine similarity between user
model and item model:
Generating Explanations
March 17th 2019 Dominguez et al ~ ACM IUI 2019 23
Friedrich, G., & Zanker, M. (2011). A
taxonomy for generating
explanations in recommender
systems. AI Magazine, 32(3), 90-98.
White-box Explanation (AVF)
March 17th 2019 Dominguez et al ~ ACM IUI 2019 24
Black-box explanation (DNN and AVF)
March 17th 2019 Dominguez et al ~ ACM IUI 2019 25
Study Procedure
March 17th 2019 Dominguez et al ~ ACM IUI 2019 26
Study Procedure
March 17th 2019 Dominguez et al ~ ACM IUI 2019 27
Study Procedure
March 17th 2019 Dominguez et al ~ ACM IUI 2019 28
Preference Elicitation
• We collect user preferences from a Pinterest-like interface
March 17th 2019 Dominguez et al ~ ACM IUI 2019 29
Study Procedure
March 17th 2019 Dominguez et al ~ ACM IUI 2019 30
Interface 1: no explanation, no transparency
March 17th 2019 Dominguez et al ~ ACM IUI 2019 31
Study Procedure
March 17th 2019 Dominguez et al ~ ACM IUI 2019 32
Interface 2: explainable, no transparency
March 17th 2019 Dominguez et al ~ ACM IUI 2019 33
Study Procedure
March 17th 2019 Dominguez et al ~ ACM IUI 2019 34
Interface 3: explainable & transparent
March 17th 2019 Dominguez et al ~ ACM IUI 2019 35
Study Procedure
March 17th 2019 Dominguez et al ~ ACM IUI 2019 36
Evaluation & Results
• Post-algorithm survey aspects (agreement1-100)
– Explainable:I understood why the art images were recommended to
me.
– Relevance:The art images recommended matched my interests.
– Diverse: The art images recommended were diverse.
– Interface Satisfaction: Overall, I am satisfied with the recommender
interface.
– Use Again: I would use this recommender system again for finding
art images in the future.
– Trust: I trusted the recommendations made.
• Finally, NASA TLX (cognitive effort)
March 17th 2019 Dominguez et al ~ ACM IUI 2019 37
Demo
March 17th 2019 Dominguez et al ~ ACM IUI 2019 38
Evaluation & Results
Study on Amazon Mechanical Turk:
● 121 valid users completed correctly the study.
● Task took them around 10 minutes to complete.
● ~56% female, 44% male.
● 80% attended to 1 or more art classes at high school level or
above.
● 80% visited museums or art galleries at least once a year.
March 17th 2019 Dominguez et al ~ ACM IUI 2019 39
Results
March 17th 2019 Dominguez et al ~ ACM IUI 2019 40
Interface 1: UI without explanation
Interface 2: UI with example-based explanation
Interface 3: UI with transparent explanation (AVF)
Results
March 17th 2019 Dominguez et al ~ ACM IUI 2019 41
7 dimensions evaluated, for DNN and AVF (scale 1-100):
Perception of:
- Explainability
- Relevance
- Diversity
- Satisfaction w/UI
- Intention of use
- Trust on RecSys
- Avg. Rating
Results
• Result 1: DNN better or equal than AVF except on diversity
March 17th 2019 Dominguez et al ~ ACM IUI 2019 42
- AVF is perceived significantly more
diverse than DNN excepting when AVF
uses transparent and explainable
recommendations.
Results
• Result 2: Explainable interfaces increase perception of
explainability.
March 17th 2019 Dominguez et al ~ ACM IUI 2019
- Result expected: people perceive the system as
more explainable using the explainable
interfaces than non explainable.
43
Results
• Result 2: Explainable interfaces increase perception of
explainability.
March 17th 2019 Dominguez et al ~ ACM IUI 2019
- Result expected: people perceive the system as
more explainable using the explainable
interfaces than non explainable.
- But this perception is significantly higher using
DNN visual features than AVF.
44
Evaluation & Results
• Result 2: Perception of relevance changes just by adding
explanations -> User Interface really matters!!
March 17th 2019 Dominguez et al ~ ACM IUI 2019
- Algorithm is the same (DNN), but by
adding explanations people perceive
recommendations as more relevant,
- Result is significant only with DNN.
45
Evaluation & Results
• Result 3: No difference in Trust between DNN and AVF in I1
(without explanations)
March 17th 2019 Dominguez et al ~ ACM IUI 2019 46
- The difference in Trust between DNN
and AVF becomes significant only
when using explainable interfaces.
Evaluation & Results
• Result 4: Without explanations, No difference between DNN
and AVF upon intention of use and satisfaction with interface.
March 17th 2019 Dominguez et al ~ ACM IUI 2019 47
- The difference on Satisfaction and
Intention of use between DNN and
AVF becomes significant only when
using explainable interfaces.
General Model: Knijnenburg Framework
March 17th 2019 Dominguez et al ~ ACM IUI 2019 48
Knijnenburg,B. P., & Willemsen,M. C. (2015).Evaluatingrecommender
systemswith user experiments.In RecommenderSystems
Handbook (pp.309-352).Springer,Boston,MA.
Visual Art RecSys Explanation Model
March 17th 2019 Dominguez et al ~ ACM IUI 2019 49
Visual Art RecSys Explanation Model
March 17th 2019 Dominguez et al ~ ACM IUI 2019 50
- Compared to the baseline interface
I1, the interface I2 (β=0.551) and
interface I3 (β=0.556) have a positive
effect on Understandability.
- The model explains 23.3% of the
variance of Understandability.
Visual Art RecSys Explanation Model
March 17th 2019 Dominguez et al ~ ACM IUI 2019 51
- Compared to the
baseline AVF, DNN
features have an strong
positive effect on
understandability
(β=0.710), as well as on
ratings (β=0.710).
Visual Art RecSys Explanation Model
March 17th 2019 Dominguez et al ~ ACM IUI 2019 52
- Perceived Effort (Insecurity, rush,
mental demand) has a significant
negative effect (β=-0.283) on
understandability.
Visual Art RecSys Explanation Model
March 17th 2019 Dominguez et al ~ ACM IUI 2019 53
- Satisfaction is strongly
affected by the Trust on
the system (+), as well
as by Understandability
(+), Time (+) and
Experience with the
domain (+).
- Trust is affected by
Understandability (+)
and by effort (-)
Conclusion
• DNN features performed better than AVF features, probably because
AlexNet is able to capture more complex patterns. Results confirm
previous work by Messina et al. (2018).
• Providing a UI with explanations has a big effect on several
dimensions evaluated. This study provides further evidence upon the
importance of user interfaces and not only algorithms as important
effects on UX with RecSys.
• Results indicate that explainability has a positive effect on UX with a
RecSys, but is not always well perceived with additional transparency.
March 17th 2019 Dominguez et al ~ ACM IUI 2019 54
Future Work
• (limitation) If additional transparency is provided in an
explanation, make sure the explanation is actually being
understood.
• Develop a full end-to-end Deep Learning art recommendation
model, rather than using pre-trained embeddings and memory-
based content-based recommendation.
• Test recent advances in XAI and visualization of CNNs into the
recommendation framework.
March 17th 2019 Dominguez et al ~ ACM IUI 2019 55
Acknowledgment
• The were funded by PUC Chile, Conicyt, Fondecyt grant
11150783, as well as by the Millennium Institute for
Foundational Research on Data (IMFD).
March 17th 2019 Dominguez et al ~ ACM IUI 2019 56
THANKS!
Denis Parra
Assistant Professor
Pontificia Universidad Católicade Chile
dparras@uc.cl
References
● Vicente Dominguez, Pablo Messina, Denis Parra, Domingo Mery, Christoph Trattner, and
Alvaro Soto. 2017. Comparing Neural and Attractiveness-based Visual Features for
Artwork Recommendation. In Proceedings of the Workshop on Deep Learning for
Recommender Systems, co-located at RecSys 2017.
● Ruining He, Chen Fang, Zhaowen Wang, and Julian McAuley. 2016. Vista: A Visually,
Socially, and Temporally-aware Model for Artistic Recommendation. In Proceedings of
the 10th ACM Conference on Recommender Systems (RecSys ’16).
● Alex Krizhevsky, Ilya Sutskever, and Geo rey E Hinton. 2012. Imagenet classi cation with
deep convolutional neural networks. In Advances in neural information processing
systems.
● Pablo Messina, Vicente Dominguez, , Denis Parra, Christoph Trattner, and Alvaro Soto.
2018. Content-Based Artwork Recommendation: Integrating Painting Metadata with
Neural and Manually-Engineered Visual Features. User Modeling and User-Adapted
Interaction (2018).
● Jose San Pedro and Stefan Siersdorfer. 2009. Ranking and Classifying Attractiveness of
Photos in Folksonomies. In Proceedings of the 18th International Conference on World
Wide Web (WWW ’09).
March 17th 2019 Dominguez et al ~ ACM IUI 2019 58

Más contenido relacionado

Similar a The Effect of Explanations & Algorithmic Accuracy on Visual Recommender Systems of Artistic Images - ACM IUI 2019

Multimedia Information Retrieval: Bytes and pixels meet the challenges of hum...
Multimedia Information Retrieval: Bytes and pixels meet the challenges of hum...Multimedia Information Retrieval: Bytes and pixels meet the challenges of hum...
Multimedia Information Retrieval: Bytes and pixels meet the challenges of hum...maranlar
 
Mind mapping and Its Applications, Introduction to Context Trees
Mind mapping and Its Applications, Introduction to Context TreesMind mapping and Its Applications, Introduction to Context Trees
Mind mapping and Its Applications, Introduction to Context TreesSunayana Gawde
 
Interactive Video Search: Where is the User in the Age of Deep Learning?
Interactive Video Search: Where is the User in the Age of Deep Learning?Interactive Video Search: Where is the User in the Age of Deep Learning?
Interactive Video Search: Where is the User in the Age of Deep Learning?klschoef
 
A picture and a thousand words: Mixing modalities to tackle new multimedia i...
A picture and a thousand words: Mixing modalities to tackle new  multimedia i...A picture and a thousand words: Mixing modalities to tackle new  multimedia i...
A picture and a thousand words: Mixing modalities to tackle new multimedia i...maranlar
 
Towards the next generation of interactive and adaptive explanation methods
Towards the next generation of interactive and adaptive explanation methodsTowards the next generation of interactive and adaptive explanation methods
Towards the next generation of interactive and adaptive explanation methodsKatrien Verbert
 
Users' experiences of new generation search interfaces: introducing Ex Libris...
Users' experiences of new generation search interfaces: introducing Ex Libris...Users' experiences of new generation search interfaces: introducing Ex Libris...
Users' experiences of new generation search interfaces: introducing Ex Libris...IL Group (CILIP Information Literacy Group)
 
MTVRep: A movie and TV show reputation system based on fine-grained sentiment ...
MTVRep: A movie and TV show reputation system based on fine-grained sentiment ...MTVRep: A movie and TV show reputation system based on fine-grained sentiment ...
MTVRep: A movie and TV show reputation system based on fine-grained sentiment ...IJECEIAES
 
Human-centered AI: towards the next generation of interactive and adaptive ex...
Human-centered AI: towards the next generation of interactive and adaptive ex...Human-centered AI: towards the next generation of interactive and adaptive ex...
Human-centered AI: towards the next generation of interactive and adaptive ex...Katrien Verbert
 
IRJET- Visual Information Narrator using Neural Network
IRJET- Visual Information Narrator using Neural NetworkIRJET- Visual Information Narrator using Neural Network
IRJET- Visual Information Narrator using Neural NetworkIRJET Journal
 
2009-Social computing-First steps to netviz nirvana
2009-Social computing-First steps to netviz nirvana2009-Social computing-First steps to netviz nirvana
2009-Social computing-First steps to netviz nirvanaMarc Smith
 
Critiquing CS Assessment from a CS for All lens: Dagstuhl Seminar Poster
Critiquing CS Assessment from a CS for All lens: Dagstuhl Seminar PosterCritiquing CS Assessment from a CS for All lens: Dagstuhl Seminar Poster
Critiquing CS Assessment from a CS for All lens: Dagstuhl Seminar PosterMark Guzdial
 
Introduction to Data Visualization
Introduction to Data Visualization Introduction to Data Visualization
Introduction to Data Visualization Ana Jofre
 
EBI Interfaces - Introductory presentation
EBI Interfaces - Introductory presentationEBI Interfaces - Introductory presentation
EBI Interfaces - Introductory presentationFrancis Rowland
 

Similar a The Effect of Explanations & Algorithmic Accuracy on Visual Recommender Systems of Artistic Images - ACM IUI 2019 (20)

Multimedia Information Retrieval: Bytes and pixels meet the challenges of hum...
Multimedia Information Retrieval: Bytes and pixels meet the challenges of hum...Multimedia Information Retrieval: Bytes and pixels meet the challenges of hum...
Multimedia Information Retrieval: Bytes and pixels meet the challenges of hum...
 
Short intro: Chung-Ching Huang
Short intro: Chung-Ching HuangShort intro: Chung-Ching Huang
Short intro: Chung-Ching Huang
 
Mind mapping and Its Applications, Introduction to Context Trees
Mind mapping and Its Applications, Introduction to Context TreesMind mapping and Its Applications, Introduction to Context Trees
Mind mapping and Its Applications, Introduction to Context Trees
 
Interactive Video Search: Where is the User in the Age of Deep Learning?
Interactive Video Search: Where is the User in the Age of Deep Learning?Interactive Video Search: Where is the User in the Age of Deep Learning?
Interactive Video Search: Where is the User in the Age of Deep Learning?
 
Paper presentation2
Paper presentation2Paper presentation2
Paper presentation2
 
Exploratory Analysis of User Data
Exploratory Analysis of User DataExploratory Analysis of User Data
Exploratory Analysis of User Data
 
A picture and a thousand words: Mixing modalities to tackle new multimedia i...
A picture and a thousand words: Mixing modalities to tackle new  multimedia i...A picture and a thousand words: Mixing modalities to tackle new  multimedia i...
A picture and a thousand words: Mixing modalities to tackle new multimedia i...
 
Technology Acceptance of Virtual Reality for Travel Planning
Technology Acceptance of Virtual Reality for Travel PlanningTechnology Acceptance of Virtual Reality for Travel Planning
Technology Acceptance of Virtual Reality for Travel Planning
 
Towards the next generation of interactive and adaptive explanation methods
Towards the next generation of interactive and adaptive explanation methodsTowards the next generation of interactive and adaptive explanation methods
Towards the next generation of interactive and adaptive explanation methods
 
Users' experiences of new generation search interfaces: introducing Ex Libris...
Users' experiences of new generation search interfaces: introducing Ex Libris...Users' experiences of new generation search interfaces: introducing Ex Libris...
Users' experiences of new generation search interfaces: introducing Ex Libris...
 
MTVRep: A movie and TV show reputation system based on fine-grained sentiment ...
MTVRep: A movie and TV show reputation system based on fine-grained sentiment ...MTVRep: A movie and TV show reputation system based on fine-grained sentiment ...
MTVRep: A movie and TV show reputation system based on fine-grained sentiment ...
 
Visual Arts students multimodal choices with Carbonmade in 2010
Visual Arts students multimodal choices with Carbonmade in 2010Visual Arts students multimodal choices with Carbonmade in 2010
Visual Arts students multimodal choices with Carbonmade in 2010
 
Human-centered AI: towards the next generation of interactive and adaptive ex...
Human-centered AI: towards the next generation of interactive and adaptive ex...Human-centered AI: towards the next generation of interactive and adaptive ex...
Human-centered AI: towards the next generation of interactive and adaptive ex...
 
IRJET- Visual Information Narrator using Neural Network
IRJET- Visual Information Narrator using Neural NetworkIRJET- Visual Information Narrator using Neural Network
IRJET- Visual Information Narrator using Neural Network
 
2009-Social computing-First steps to netviz nirvana
2009-Social computing-First steps to netviz nirvana2009-Social computing-First steps to netviz nirvana
2009-Social computing-First steps to netviz nirvana
 
Critiquing CS Assessment from a CS for All lens: Dagstuhl Seminar Poster
Critiquing CS Assessment from a CS for All lens: Dagstuhl Seminar PosterCritiquing CS Assessment from a CS for All lens: Dagstuhl Seminar Poster
Critiquing CS Assessment from a CS for All lens: Dagstuhl Seminar Poster
 
Introduction to Data Visualization
Introduction to Data Visualization Introduction to Data Visualization
Introduction to Data Visualization
 
PerabathiniH-Oct222015
PerabathiniH-Oct222015PerabathiniH-Oct222015
PerabathiniH-Oct222015
 
Data analysis
Data analysisData analysis
Data analysis
 
EBI Interfaces - Introductory presentation
EBI Interfaces - Introductory presentationEBI Interfaces - Introductory presentation
EBI Interfaces - Introductory presentation
 

Más de Denis Parra Santander

Human-Centered Machine Learning: Harnessing Visualization and Interactivity f...
Human-Centered Machine Learning: Harnessing Visualization and Interactivity f...Human-Centered Machine Learning: Harnessing Visualization and Interactivity f...
Human-Centered Machine Learning: Harnessing Visualization and Interactivity f...Denis Parra Santander
 
Data Fusion for Dealing with the Recommendation Problem
Data Fusion for Dealing with the Recommendation ProblemData Fusion for Dealing with the Recommendation Problem
Data Fusion for Dealing with the Recommendation ProblemDenis Parra Santander
 
Identifying Relevant Messages in a Twitter-based Citizen Channel for Natural ...
Identifying Relevant Messages in a Twitter-based Citizen Channel for Natural ...Identifying Relevant Messages in a Twitter-based Citizen Channel for Natural ...
Identifying Relevant Messages in a Twitter-based Citizen Channel for Natural ...Denis Parra Santander
 
Research on Recommender Systems: Beyond Ratings and Lists
Research on Recommender Systems: Beyond Ratings and ListsResearch on Recommender Systems: Beyond Ratings and Lists
Research on Recommender Systems: Beyond Ratings and ListsDenis Parra Santander
 
The Effect of Different Set-based Visualizations on User Exploration of Reco...
The Effect of Different Set-based  Visualizations on User Exploration of Reco...The Effect of Different Set-based  Visualizations on User Exploration of Reco...
The Effect of Different Set-based Visualizations on User Exploration of Reco...Denis Parra Santander
 
SetFusion Visual Hybrid Recommender - IUI 2014
SetFusion Visual Hybrid Recommender -  IUI 2014SetFusion Visual Hybrid Recommender -  IUI 2014
SetFusion Visual Hybrid Recommender - IUI 2014Denis Parra Santander
 
Walk the Talk: Analyzing the relation between implicit and explicit feedback ...
Walk the Talk: Analyzing the relation between implicit and explicit feedback ...Walk the Talk: Analyzing the relation between implicit and explicit feedback ...
Walk the Talk: Analyzing the relation between implicit and explicit feedback ...Denis Parra Santander
 
Network Visualization guest lecture at #DataVizQMSS at @Columbia / #SNA at PU...
Network Visualization guest lecture at #DataVizQMSS at @Columbia / #SNA at PU...Network Visualization guest lecture at #DataVizQMSS at @Columbia / #SNA at PU...
Network Visualization guest lecture at #DataVizQMSS at @Columbia / #SNA at PU...Denis Parra Santander
 
A Hybrid Peer Recommender System for a Online Community Teachers
A Hybrid Peer Recommender System for a Online Community TeachersA Hybrid Peer Recommender System for a Online Community Teachers
A Hybrid Peer Recommender System for a Online Community TeachersDenis Parra Santander
 
Implicit Feedback Recommendation via Implicit-to-Explicit Ordinal Logistic Re...
Implicit Feedback Recommendation via Implicit-to-Explicit Ordinal Logistic Re...Implicit Feedback Recommendation via Implicit-to-Explicit Ordinal Logistic Re...
Implicit Feedback Recommendation via Implicit-to-Explicit Ordinal Logistic Re...Denis Parra Santander
 
Currents steps to be a researcher and faculty
Currents steps to be a researcher and facultyCurrents steps to be a researcher and faculty
Currents steps to be a researcher and facultyDenis Parra Santander
 
Evaluation of Collaborative Filtering Algorithms for Recommending Articles on...
Evaluation of Collaborative Filtering Algorithms for Recommending Articles on...Evaluation of Collaborative Filtering Algorithms for Recommending Articles on...
Evaluation of Collaborative Filtering Algorithms for Recommending Articles on...Denis Parra Santander
 

Más de Denis Parra Santander (15)

Human-Centered Machine Learning: Harnessing Visualization and Interactivity f...
Human-Centered Machine Learning: Harnessing Visualization and Interactivity f...Human-Centered Machine Learning: Harnessing Visualization and Interactivity f...
Human-Centered Machine Learning: Harnessing Visualization and Interactivity f...
 
Interactive Recommender Systems
Interactive Recommender SystemsInteractive Recommender Systems
Interactive Recommender Systems
 
Data Fusion for Dealing with the Recommendation Problem
Data Fusion for Dealing with the Recommendation ProblemData Fusion for Dealing with the Recommendation Problem
Data Fusion for Dealing with the Recommendation Problem
 
LDA on social bookmarking systems
LDA on social bookmarking systemsLDA on social bookmarking systems
LDA on social bookmarking systems
 
Identifying Relevant Messages in a Twitter-based Citizen Channel for Natural ...
Identifying Relevant Messages in a Twitter-based Citizen Channel for Natural ...Identifying Relevant Messages in a Twitter-based Citizen Channel for Natural ...
Identifying Relevant Messages in a Twitter-based Citizen Channel for Natural ...
 
Research on Recommender Systems: Beyond Ratings and Lists
Research on Recommender Systems: Beyond Ratings and ListsResearch on Recommender Systems: Beyond Ratings and Lists
Research on Recommender Systems: Beyond Ratings and Lists
 
The Effect of Different Set-based Visualizations on User Exploration of Reco...
The Effect of Different Set-based  Visualizations on User Exploration of Reco...The Effect of Different Set-based  Visualizations on User Exploration of Reco...
The Effect of Different Set-based Visualizations on User Exploration of Reco...
 
Twitter in Academic Conferences
Twitter in Academic ConferencesTwitter in Academic Conferences
Twitter in Academic Conferences
 
SetFusion Visual Hybrid Recommender - IUI 2014
SetFusion Visual Hybrid Recommender -  IUI 2014SetFusion Visual Hybrid Recommender -  IUI 2014
SetFusion Visual Hybrid Recommender - IUI 2014
 
Walk the Talk: Analyzing the relation between implicit and explicit feedback ...
Walk the Talk: Analyzing the relation between implicit and explicit feedback ...Walk the Talk: Analyzing the relation between implicit and explicit feedback ...
Walk the Talk: Analyzing the relation between implicit and explicit feedback ...
 
Network Visualization guest lecture at #DataVizQMSS at @Columbia / #SNA at PU...
Network Visualization guest lecture at #DataVizQMSS at @Columbia / #SNA at PU...Network Visualization guest lecture at #DataVizQMSS at @Columbia / #SNA at PU...
Network Visualization guest lecture at #DataVizQMSS at @Columbia / #SNA at PU...
 
A Hybrid Peer Recommender System for a Online Community Teachers
A Hybrid Peer Recommender System for a Online Community TeachersA Hybrid Peer Recommender System for a Online Community Teachers
A Hybrid Peer Recommender System for a Online Community Teachers
 
Implicit Feedback Recommendation via Implicit-to-Explicit Ordinal Logistic Re...
Implicit Feedback Recommendation via Implicit-to-Explicit Ordinal Logistic Re...Implicit Feedback Recommendation via Implicit-to-Explicit Ordinal Logistic Re...
Implicit Feedback Recommendation via Implicit-to-Explicit Ordinal Logistic Re...
 
Currents steps to be a researcher and faculty
Currents steps to be a researcher and facultyCurrents steps to be a researcher and faculty
Currents steps to be a researcher and faculty
 
Evaluation of Collaborative Filtering Algorithms for Recommending Articles on...
Evaluation of Collaborative Filtering Algorithms for Recommending Articles on...Evaluation of Collaborative Filtering Algorithms for Recommending Articles on...
Evaluation of Collaborative Filtering Algorithms for Recommending Articles on...
 

Último

Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxKatpro Technologies
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Allon Mureinik
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonAnna Loughnan Colquhoun
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEarley Information Science
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Igalia
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Servicegiselly40
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesSinan KOZAK
 
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsTop 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsRoshan Dwivedi
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfEnterprise Knowledge
 
Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilV3cube
 
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...gurkirankumar98700
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountPuma Security, LLC
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slidespraypatel2
 

Último (20)

Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen Frames
 
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsTop 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
 
Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of Brazil
 
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path Mount
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
 

The Effect of Explanations & Algorithmic Accuracy on Visual Recommender Systems of Artistic Images - ACM IUI 2019

  • 1. The Effect of Explanations and Algorithmic Accuracy on Visual Recommender Systems of Artistic Images Pontificia UniversidadCatólica de Chile (PUC Chile) Vicente Domínguez Pablo Messina Ivania Donoso-Guzmán Denis Parra
  • 2. The Effect of Explanations and Algorithmic Accuracy on Visual Recommender Systems of Artistic Images (candidate to best paper) Pontificia UniversidadCatólica de Chile (PUC Chile) Vicente Domínguez Pablo Messina Ivania Donoso-Guzmán Denis Parra
  • 3. The Online Artwork Market • Online artwork market: Growing since 2008, despite global crises! • In 2011, art received $11.57 billion in total global annual revenue, over $2 billion versus 2010 (*forbes) • Recommender systems could play an important role, just like in other e-commerce industries. [forbes] https://www.forbes.com/sites/abigailesman/2012/02/29/ the- worlds- strongest- economy- the- global- art- market/ (2012) March 17th 2019 Dominguez et al ~ ACM IUI 2019 3
  • 4. Related Work: Art Recommendation March 17th 2019 Dominguez et al ~ ACM IUI 2019 4 • Previous art recommendationprojects date for as long as 2007, such as the CHIP project to recommend paintings from Rijksmuseum. (Aroyo et al., 2007) • Some approaches have used: – Ratings (Aroyo et al., 2007), – Tags, Keywords or other textual features (Semeraro et al. 2012) – Traditional visual features (van den Broek et al., 2006) • Deep Learning (DL) have revolutionized visual feature learning, but few works use them for recommending art (Het et al. 2016,Messina et al. 2018)
  • 5. Related Work: Art Recommendation March 17th 2019 Dominguez et al ~ ACM IUI 2019 5 • Previous art recommendationprojects date for as long as 2007, such as the CHIP project to recommend paintings from Rijksmuseum. (Aroyo et al., 2007) • Some approaches have used: – Ratings (Aroyo et al., 2007), – Tags, Keywords or other textual features (Semeraro et al. 2012) – Traditional visual features (van den Broek et al., 2006) • Deep Learning (DL) have revolutionized visual feature learning, but few works use them for recommending art (Het et al. 2016,Messina et al. 2018)
  • 6. Related Work: Art Recommendation • Previous art recommendationprojects date for as long as 2007, such as the CHIP project to recommend paintings from Rijksmuseum. (Aroyo et al., 2007) • Some approaches have used: – Ratings (Aroyo et al., 2007), – Tags, Keywords or other textual features (Semeraro et al. 2012) – Traditional visual features (van den Broek et al., 2006) • Deep Learning (DL) have revolutionized computer vision, but few works use DL methods for recommending art (He et al. 2016,Messina et al. 2018) March 17th 2019 Dominguez et al ~ ACM IUI 2019 6
  • 7. Our Approach to Image Recommendation • Since 2017 we have been working on recommending art images, using mostly content-based methods. • Four papers published: – ACM DLRS 2017: Dominguez,V.,Messina,P., Parra, D., Mery, D., Trattner,C., & Soto,A. (2017,August).Comparing Neural and Attractivenessbased Visual Features forArtwork Recommendation.In Proceedingsof the2nd Workshop on Deep Learning for RecommenderSystems(pp.55-59).ACM. – UMUAI 2018: Messina,P., Dominguez,V.,Parra, D., Trattner,C., & Soto, A. (2018).Content- based artwork recommendation:integrating paintingmetadatawith neural and manually- engineered visual features.UserModeling and User-Adapted Interaction,1-40. – Two additional workshop papers in ACM RecSys 2018. March 17th 2019 Dominguez et al ~ ACM IUI 2019 7
  • 8. Open Questions from Content-Based RecSys • We learned that visual features from DNNs perform better than attractiveness visual features. March 17th 2019 Dominguez et al ~ ACM IUI 2019 8 Average brightness Saturation Sharpness Entropy RGB-contrast Colorfulness Naturalness Predictive Accuracy Attractiveness visual features Deep Learning visual features
  • 9. Open Questions from Content-Based RecSys • We learned that visual features from DNNs perform better than attractiveness visual features, but they are harder to explain. March 17th 2019 Dominguez et al ~ ACM IUI 2019 9 Predictive Accuracy Explainability Average brightness Saturation Sharpness Entropy RGB-contrast Colorfulness Naturalness Attractiveness visual features Deep Learning visual features
  • 10. Explainability in Recommender Systems • Explaining recommendations is a well-established and active area of research, but there is little research on explaining image recommendations. March 17th 2019 Dominguez et al ~ ACM IUI 2019 Herlocker, J. L., Konstan, J. A., & Riedl, J. (2000). Explaining collaborative filtering recommendations. In Proceedings of the 2000 ACM conference on Computer supported cooperative work (pp. 241-250) 10 Tintarev, N., & Masthoff, J. (2015). Explaining recommendations: Design and evaluation. In Recommender systems handbook (pp. 353- 382). Springer, Boston, MA.
  • 11. Gaining Inspiration from DARPA XAI March 17th 2019 Dominguez et al ~ ACM IUI 2019 11 DARPA XAI (Gunning, 2017) Decision Tree DNN
  • 12. DARPA XAI inspiration March 17th 2019 Dominguez et al ~ ACM IUI 2019 12 DARPA XAI (Gunning, 2017) Decision Tree DNN Our research AVF DNN VF Explainability Potential PredictiveAccuracy Is there an effect on user perception if we provide a UI with explanations?
  • 13. Our General Research Question • Explainable & Transparent UIs are well perceived by users in previous RecSys research, but: Does it matter to UX if you do not produce accurate enough predictions? March 17th 2019 Dominguez et al ~ ACM IUI 2019 13 AVF DNN VF Explainability Potential PredictiveAccuracy - UI w/explanation based on examples - UI w/explanation based on examples or visual features
  • 14. Research Questions • RQ1. Given three different types of interfaces, one baseline interface without explanations and two with explanations but different levels of transparency, which one is perceived as most useful? • RQ2. Furthermore, based on the visual content-based recommenderalgorithm chosen (DNN or AVF), are there observable differences in how the three interfaces are perceived? • RQ3. How do independent variables such as algorithm, explainable interface and domain knowledge interact in order to explain the user experience with the recommender system in terms of perception of relevance, diversity, explainabilityand user satisfaction? March 17th 2019 Dominguez et al ~ ACM IUI 2019 14
  • 15. Research Questions • RQ1. Given three different types of interfaces, one baseline interface without explanations and two with explanations but different levels of transparency, which one is perceived as most useful? • RQ2. Furthermore, based on the visual content-based recommenderalgorithm chosen (DNN or AVF), are there observable differences in how the three interfaces are perceived? • RQ3. How do independent variables such as algorithm, explainable interface and domain knowledge interact in order to explain the user experience with the recommender system in terms of perception of relevance, diversity, explainabilityand user satisfaction? March 17th 2019 Dominguez et al ~ ACM IUI 2019 15
  • 16. Research Questions • RQ1. Given three different types of interfaces, one baseline interface without explanations and two with explanations but different levels of transparency, which one is perceived as most useful? • RQ2. Furthermore, based on the visual content-based recommenderalgorithm chosen (DNN or AVF), are there observable differences in how the three interfaces are perceived? • RQ3. How do independent variables such as algorithm, explainable interface and domain knowledge interact in order to explain the user experience with the recommender system in terms of perception of relevance, diversity, explainabilityand user satisfaction? March 17th 2019 Dominguez et al ~ ACM IUI 2019 16
  • 17. Materials and Methodology 1. We collect image data from UGallery, an online store of physical artworks (paintings and photographs). 2. We implement a system which records user preferences and generates recommendations. Some of these recommendations will have explanations. 3. We conduct a user study in Amazon Mechanical Turk to assess the impact of algorithmic accuracy and explainable UI on several user dimensions. March 17th 2019 Dominguez et al ~ ACM IUI 2019 17
  • 18. Data: UGallery • Online Artwork Store, based on CA, USA. • Mostly sales one- of-a-kind physical artwork. March 17th 2019 Dominguez et al ~ ACM IUI 2019 18
  • 19. CB RecSys algorithm: Visual Features • (DNN) Deep Neural Networks • (AVF) Attractiveness- based March 17th 2019 Dominguez et al ~ ACM IUI 2019 19
  • 20. Visual Features: DNN vs. AVF • Deep Neural Networks (DNN): we used an AlexNet DNN (pre-trained with ImageNet ILSVRC 2012 dataset) (Krizhevsky et al, 2012) • We map each artwork image to its corresponding latent vector of 4,096 dimensions obtained at the fc6 layer of the AlexNet network.
  • 21. Visual Features: AVF • Average brightness, • Saturation, • Sharpness, • Entropy, • RGB-contrast, • Colorfulness, • Naturalness Jose San Pedro and Stefan Siersdorfer. 2009. Ranking andClassifying Attractiveness of Photos in Folksonomies. In Proceedings of the 18thInternational Conference on World Wide Web (WWW’09). March 17th 2019 Dominguez et al ~ ACM IUI 2019 21
  • 22. UGallery: Making Recommendations • Scoring items based on cosine similarity between user model and item model:
  • 23. Generating Explanations March 17th 2019 Dominguez et al ~ ACM IUI 2019 23 Friedrich, G., & Zanker, M. (2011). A taxonomy for generating explanations in recommender systems. AI Magazine, 32(3), 90-98.
  • 24. White-box Explanation (AVF) March 17th 2019 Dominguez et al ~ ACM IUI 2019 24
  • 25. Black-box explanation (DNN and AVF) March 17th 2019 Dominguez et al ~ ACM IUI 2019 25
  • 26. Study Procedure March 17th 2019 Dominguez et al ~ ACM IUI 2019 26
  • 27. Study Procedure March 17th 2019 Dominguez et al ~ ACM IUI 2019 27
  • 28. Study Procedure March 17th 2019 Dominguez et al ~ ACM IUI 2019 28
  • 29. Preference Elicitation • We collect user preferences from a Pinterest-like interface March 17th 2019 Dominguez et al ~ ACM IUI 2019 29
  • 30. Study Procedure March 17th 2019 Dominguez et al ~ ACM IUI 2019 30
  • 31. Interface 1: no explanation, no transparency March 17th 2019 Dominguez et al ~ ACM IUI 2019 31
  • 32. Study Procedure March 17th 2019 Dominguez et al ~ ACM IUI 2019 32
  • 33. Interface 2: explainable, no transparency March 17th 2019 Dominguez et al ~ ACM IUI 2019 33
  • 34. Study Procedure March 17th 2019 Dominguez et al ~ ACM IUI 2019 34
  • 35. Interface 3: explainable & transparent March 17th 2019 Dominguez et al ~ ACM IUI 2019 35
  • 36. Study Procedure March 17th 2019 Dominguez et al ~ ACM IUI 2019 36
  • 37. Evaluation & Results • Post-algorithm survey aspects (agreement1-100) – Explainable:I understood why the art images were recommended to me. – Relevance:The art images recommended matched my interests. – Diverse: The art images recommended were diverse. – Interface Satisfaction: Overall, I am satisfied with the recommender interface. – Use Again: I would use this recommender system again for finding art images in the future. – Trust: I trusted the recommendations made. • Finally, NASA TLX (cognitive effort) March 17th 2019 Dominguez et al ~ ACM IUI 2019 37
  • 38. Demo March 17th 2019 Dominguez et al ~ ACM IUI 2019 38
  • 39. Evaluation & Results Study on Amazon Mechanical Turk: ● 121 valid users completed correctly the study. ● Task took them around 10 minutes to complete. ● ~56% female, 44% male. ● 80% attended to 1 or more art classes at high school level or above. ● 80% visited museums or art galleries at least once a year. March 17th 2019 Dominguez et al ~ ACM IUI 2019 39
  • 40. Results March 17th 2019 Dominguez et al ~ ACM IUI 2019 40 Interface 1: UI without explanation Interface 2: UI with example-based explanation Interface 3: UI with transparent explanation (AVF)
  • 41. Results March 17th 2019 Dominguez et al ~ ACM IUI 2019 41 7 dimensions evaluated, for DNN and AVF (scale 1-100): Perception of: - Explainability - Relevance - Diversity - Satisfaction w/UI - Intention of use - Trust on RecSys - Avg. Rating
  • 42. Results • Result 1: DNN better or equal than AVF except on diversity March 17th 2019 Dominguez et al ~ ACM IUI 2019 42 - AVF is perceived significantly more diverse than DNN excepting when AVF uses transparent and explainable recommendations.
  • 43. Results • Result 2: Explainable interfaces increase perception of explainability. March 17th 2019 Dominguez et al ~ ACM IUI 2019 - Result expected: people perceive the system as more explainable using the explainable interfaces than non explainable. 43
  • 44. Results • Result 2: Explainable interfaces increase perception of explainability. March 17th 2019 Dominguez et al ~ ACM IUI 2019 - Result expected: people perceive the system as more explainable using the explainable interfaces than non explainable. - But this perception is significantly higher using DNN visual features than AVF. 44
  • 45. Evaluation & Results • Result 2: Perception of relevance changes just by adding explanations -> User Interface really matters!! March 17th 2019 Dominguez et al ~ ACM IUI 2019 - Algorithm is the same (DNN), but by adding explanations people perceive recommendations as more relevant, - Result is significant only with DNN. 45
  • 46. Evaluation & Results • Result 3: No difference in Trust between DNN and AVF in I1 (without explanations) March 17th 2019 Dominguez et al ~ ACM IUI 2019 46 - The difference in Trust between DNN and AVF becomes significant only when using explainable interfaces.
  • 47. Evaluation & Results • Result 4: Without explanations, No difference between DNN and AVF upon intention of use and satisfaction with interface. March 17th 2019 Dominguez et al ~ ACM IUI 2019 47 - The difference on Satisfaction and Intention of use between DNN and AVF becomes significant only when using explainable interfaces.
  • 48. General Model: Knijnenburg Framework March 17th 2019 Dominguez et al ~ ACM IUI 2019 48 Knijnenburg,B. P., & Willemsen,M. C. (2015).Evaluatingrecommender systemswith user experiments.In RecommenderSystems Handbook (pp.309-352).Springer,Boston,MA.
  • 49. Visual Art RecSys Explanation Model March 17th 2019 Dominguez et al ~ ACM IUI 2019 49
  • 50. Visual Art RecSys Explanation Model March 17th 2019 Dominguez et al ~ ACM IUI 2019 50 - Compared to the baseline interface I1, the interface I2 (β=0.551) and interface I3 (β=0.556) have a positive effect on Understandability. - The model explains 23.3% of the variance of Understandability.
  • 51. Visual Art RecSys Explanation Model March 17th 2019 Dominguez et al ~ ACM IUI 2019 51 - Compared to the baseline AVF, DNN features have an strong positive effect on understandability (β=0.710), as well as on ratings (β=0.710).
  • 52. Visual Art RecSys Explanation Model March 17th 2019 Dominguez et al ~ ACM IUI 2019 52 - Perceived Effort (Insecurity, rush, mental demand) has a significant negative effect (β=-0.283) on understandability.
  • 53. Visual Art RecSys Explanation Model March 17th 2019 Dominguez et al ~ ACM IUI 2019 53 - Satisfaction is strongly affected by the Trust on the system (+), as well as by Understandability (+), Time (+) and Experience with the domain (+). - Trust is affected by Understandability (+) and by effort (-)
  • 54. Conclusion • DNN features performed better than AVF features, probably because AlexNet is able to capture more complex patterns. Results confirm previous work by Messina et al. (2018). • Providing a UI with explanations has a big effect on several dimensions evaluated. This study provides further evidence upon the importance of user interfaces and not only algorithms as important effects on UX with RecSys. • Results indicate that explainability has a positive effect on UX with a RecSys, but is not always well perceived with additional transparency. March 17th 2019 Dominguez et al ~ ACM IUI 2019 54
  • 55. Future Work • (limitation) If additional transparency is provided in an explanation, make sure the explanation is actually being understood. • Develop a full end-to-end Deep Learning art recommendation model, rather than using pre-trained embeddings and memory- based content-based recommendation. • Test recent advances in XAI and visualization of CNNs into the recommendation framework. March 17th 2019 Dominguez et al ~ ACM IUI 2019 55
  • 56. Acknowledgment • The were funded by PUC Chile, Conicyt, Fondecyt grant 11150783, as well as by the Millennium Institute for Foundational Research on Data (IMFD). March 17th 2019 Dominguez et al ~ ACM IUI 2019 56
  • 57. THANKS! Denis Parra Assistant Professor Pontificia Universidad Católicade Chile dparras@uc.cl
  • 58. References ● Vicente Dominguez, Pablo Messina, Denis Parra, Domingo Mery, Christoph Trattner, and Alvaro Soto. 2017. Comparing Neural and Attractiveness-based Visual Features for Artwork Recommendation. In Proceedings of the Workshop on Deep Learning for Recommender Systems, co-located at RecSys 2017. ● Ruining He, Chen Fang, Zhaowen Wang, and Julian McAuley. 2016. Vista: A Visually, Socially, and Temporally-aware Model for Artistic Recommendation. In Proceedings of the 10th ACM Conference on Recommender Systems (RecSys ’16). ● Alex Krizhevsky, Ilya Sutskever, and Geo rey E Hinton. 2012. Imagenet classi cation with deep convolutional neural networks. In Advances in neural information processing systems. ● Pablo Messina, Vicente Dominguez, , Denis Parra, Christoph Trattner, and Alvaro Soto. 2018. Content-Based Artwork Recommendation: Integrating Painting Metadata with Neural and Manually-Engineered Visual Features. User Modeling and User-Adapted Interaction (2018). ● Jose San Pedro and Stefan Siersdorfer. 2009. Ranking and Classifying Attractiveness of Photos in Folksonomies. In Proceedings of the 18th International Conference on World Wide Web (WWW ’09). March 17th 2019 Dominguez et al ~ ACM IUI 2019 58