SlideShare a Scribd company logo
1 of 26
EXPLANATIONS IN
RECOMMENDER SYSTEMS
Overview And Research Approaches

Mohammed Zuhair Al-Taie
AL-Salam University College
-- Iraq –
Email: mza004@live.aul.edu.lb

This study was published in “The International Arab
This study was published in “The International Arab
Conference on Information Technology (ACIT)” December
Conference on Information Technology (ACIT)” December
-2013
-2013
Goal of the study
 The goal of this study to survey & comprehend the
main

streams

of

research

in

the

field

of

Explanations in Recommender Systems and put
them in one integral work.
 It starts by explaining the main concepts of the
field and then moves on to present and discuss the
various sub-topics that took much interest from
researchers.

2
3
What Are Recommender System (RS)?
 Also called Recommendation Systems, they are
software

tools

and

techniques

providing

suggestions for items to be of use to a user.

Benefits
 RS are being well used in various application
domains such as music, videos, queries, news,
friends on social networks etc..

4
Amazon’s Recommendation System

5
Explanations in Recommender System
 Important pieces of information that are used by
both selling and buying agents, through their
communication

process,

to

increase

their

performance.
 Another definition … it is a description that makes
users better realize if the recommended item is
relevant to their needs or not

6
Explanations - Examples
YouTube
Explanation System
AR
estaurant
Recommendation Explanation

7
Explanations - Example

Amazon
Explanation System

8
?Why Using Explanations in RS

9
Phrases Expressing Explanations
 More on this artist …
 Try something from similar
artists …
 Someone similar to you also
like this …
 As you listened to that, you
may want this …
 These two go together …
 This is highly rated …
 Try something new …
 Similar or related products

 Complementary
accessories ...
 Gift idea ...
 Welcome back (recently
viewed) …
 For you today …
 New for you …
 Hot / Most popular of this
type …
 Other people also do this
…

…
10
Explanations – A Short History
 The importance of explanations has been well
identified in pervious paradigms such as Expert
Systems.
 Due to the decline of studies in Expert Systems in
the 1990s, Recommender Systems borrowed the
concepts of explanations.
 A seminal study by Herlocker et al. in 2000 on
explanations

in

RS,

which

stated

that

recommender systems had worked as black boxes,
lead the body of research in explanations to grow.

11
…However
 There are many types of explanations and various
goals they can achieve.
 Goals such as: effectiveness, efficiency,
transparency, trustworthiness, validity.. can not
all be achieved in one system at one time.
Therefore, a deep understanding of explanations
and their effects on customers is of great
importance.

12
Types of explanations in RS
 Different criteria to classify
explanations …

13
RS Explanation Styles
 Explanation styles are related to the methods
used to generate explanations.
 The most commonly-used explanation styles are:

14
15
Research Approaches in Explanations
 Researchers spread their efforts across different
research aspects. Generally, they can be divided
into two approaches:

16
Explanations Attributes (Goals)
 Explanation
attributes
are
the
benefits
that
explanations give to recommender systems. These
benefits fall into the following 11 aims:

17
.(Explanations Attributes (Cont
Transparency- 1
Provide information so the user can comprehend the reasoning
used to generate a specific recommendation
Validity- 2
Allow a user to check the validity of a recommendation
Trustworthiness- 3
A mechanism for reducing the complexity of human decision
making in uncertain situations
Persuasiveness- 4
Persuasive explanations for recommendations aim to change the
user's buying behavior. E.g., a recommender may intentionally
dwell on a product's positive aspects and keep quiet about various
negative aspects

18
.(Explanations Attributes (Cont
Scrutability- 5
means that users can tell if the system is wrong
Effectiveness- 6
Help users make better decisions
Efficiency- 7
Reduce the decision-making effort
Reduce the time needed for decision making
Satisfaction- 8
Improve the overall satisfaction stemming from the use of a
recommender system
Relevance- 9
Explanations can be provided to justify why additional
information is needed from the user

19
.(Explanations Attributes (Cont
Comprehensibility- 10
Recommenders can never be sure about the knowledge of their
users. Therefore explanations support the user by relating the
user's known concepts to the concepts employed by the
recommender
Education- 11
Educate users to help them better understand the product
domain. So, as customers become more informed, they are
able to make wiser purchasing decisions

20
Other Research Directions
Other than explanation attributes, researchers are
investigating a number of different approaches. Among
them are the following three important fields:
1. Explanation Interfaces
2. Decision Making
3. Over and Under Estimation

21
Explanation Interfaces( 1
 Explanation Interface is the technique used to control the
format by which explanations are presented to a user
(meaning that how explanations are shown to users).
Motives:
 The importance of a good interface is that it can better
explain recommendations and can even push users to make
further requests.
 The use of modalities such as text, graphs, tables,
images and colors can better present explanations to
users. For example:

22
Decision Making( 2

23
Over and Underestimation( 3
Over and Underestimation: overestimation means that
users may try a product they do not end up liking.
underestimation means that users miss products they might
have appreciated
Motives:
Overestimation may lead users later on to distrust the system
after discovering that the items it recommended were not that
useful. On the other hand under estimation may make users
miss items that fitted their interests and eventually make them
distrust the system.

24
Open Challenges
A number of challenges are still waiting to be probed by
people working in the field:

25
!THANK YOU

More Related Content

Similar to Recommender Systems Explained: Research on Using Explanations

An approach for explaining group recommendations based on negotiation informa...
An approach for explaining group recommendations based on negotiation informa...An approach for explaining group recommendations based on negotiation informa...
An approach for explaining group recommendations based on negotiation informa...IAESIJAI
 
Discover Requirement
Discover RequirementDiscover Requirement
Discover Requirementzeyadtarek13
 
3rd Workshop on Social Information Retrieval for Technology-Enhanced Learnin...
3rd Workshop onSocial  Information Retrieval for Technology-Enhanced Learnin...3rd Workshop onSocial  Information Retrieval for Technology-Enhanced Learnin...
3rd Workshop on Social Information Retrieval for Technology-Enhanced Learnin...Hendrik Drachsler
 
Explaining recommendations: design implications and lessons learned
Explaining recommendations: design implications and lessons learnedExplaining recommendations: design implications and lessons learned
Explaining recommendations: design implications and lessons learnedKatrien Verbert
 
Ux matters2016-final
Ux matters2016-finalUx matters2016-final
Ux matters2016-finalNada Cbo
 
OGD new generation infrastructures evaluation based on value models
OGD new generation infrastructures evaluation based on value modelsOGD new generation infrastructures evaluation based on value models
OGD new generation infrastructures evaluation based on value modelsCharalampos Alexopoulos
 
2012 in tech-usability_of_interfaces (1)
2012 in tech-usability_of_interfaces (1)2012 in tech-usability_of_interfaces (1)
2012 in tech-usability_of_interfaces (1)Mahesh Kate
 
Investigating Crowdsourcing as an Evaluation Method for (TEL) Recommender Sy...
Investigating Crowdsourcing as an Evaluation Method for (TEL) Recommender Sy...Investigating Crowdsourcing as an Evaluation Method for (TEL) Recommender Sy...
Investigating Crowdsourcing as an Evaluation Method for (TEL) Recommender Sy...Christoph Rensing
 
Open Data Infrastructures Evaluation Framework using Value Modelling
Open Data Infrastructures Evaluation Framework using Value Modelling Open Data Infrastructures Evaluation Framework using Value Modelling
Open Data Infrastructures Evaluation Framework using Value Modelling Yannis Charalabidis
 
Product UI/UX : How a product takes shape
Product UI/UX : How a product takes shapeProduct UI/UX : How a product takes shape
Product UI/UX : How a product takes shapeAmanjot Malhotra
 
Seffah iess11 keynote the human side of service science
Seffah iess11 keynote   the human side of service scienceSeffah iess11 keynote   the human side of service science
Seffah iess11 keynote the human side of service scienceIESS
 
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)IJERD Editor
 

Similar to Recommender Systems Explained: Research on Using Explanations (20)

Visualization of explanations in recommender systems
Visualization of explanations in recommender systemsVisualization of explanations in recommender systems
Visualization of explanations in recommender systems
 
An approach for explaining group recommendations based on negotiation informa...
An approach for explaining group recommendations based on negotiation informa...An approach for explaining group recommendations based on negotiation informa...
An approach for explaining group recommendations based on negotiation informa...
 
Discover Requirement
Discover RequirementDiscover Requirement
Discover Requirement
 
3rd Workshop on Social Information Retrieval for Technology-Enhanced Learnin...
3rd Workshop onSocial  Information Retrieval for Technology-Enhanced Learnin...3rd Workshop onSocial  Information Retrieval for Technology-Enhanced Learnin...
3rd Workshop on Social Information Retrieval for Technology-Enhanced Learnin...
 
Sirtel Workshop
Sirtel WorkshopSirtel Workshop
Sirtel Workshop
 
Explaining recommendations: design implications and lessons learned
Explaining recommendations: design implications and lessons learnedExplaining recommendations: design implications and lessons learned
Explaining recommendations: design implications and lessons learned
 
Software evaluation via users’ feedback at runtime
Software evaluation via users’ feedback at runtimeSoftware evaluation via users’ feedback at runtime
Software evaluation via users’ feedback at runtime
 
Ux matters2016-final
Ux matters2016-finalUx matters2016-final
Ux matters2016-final
 
Ijetr021224
Ijetr021224Ijetr021224
Ijetr021224
 
Ijetr021224
Ijetr021224Ijetr021224
Ijetr021224
 
OGD new generation infrastructures evaluation based on value models
OGD new generation infrastructures evaluation based on value modelsOGD new generation infrastructures evaluation based on value models
OGD new generation infrastructures evaluation based on value models
 
2012 in tech-usability_of_interfaces (1)
2012 in tech-usability_of_interfaces (1)2012 in tech-usability_of_interfaces (1)
2012 in tech-usability_of_interfaces (1)
 
IR UNIT V.docx
IR UNIT  V.docxIR UNIT  V.docx
IR UNIT V.docx
 
Investigating Crowdsourcing as an Evaluation Method for (TEL) Recommender Sy...
Investigating Crowdsourcing as an Evaluation Method for (TEL) Recommender Sy...Investigating Crowdsourcing as an Evaluation Method for (TEL) Recommender Sy...
Investigating Crowdsourcing as an Evaluation Method for (TEL) Recommender Sy...
 
Open Data Infrastructures Evaluation Framework using Value Modelling
Open Data Infrastructures Evaluation Framework using Value Modelling Open Data Infrastructures Evaluation Framework using Value Modelling
Open Data Infrastructures Evaluation Framework using Value Modelling
 
Knowledge Services
Knowledge ServicesKnowledge Services
Knowledge Services
 
Data Flow Chart
Data Flow ChartData Flow Chart
Data Flow Chart
 
Product UI/UX : How a product takes shape
Product UI/UX : How a product takes shapeProduct UI/UX : How a product takes shape
Product UI/UX : How a product takes shape
 
Seffah iess11 keynote the human side of service science
Seffah iess11 keynote   the human side of service scienceSeffah iess11 keynote   the human side of service science
Seffah iess11 keynote the human side of service science
 
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)
 

More from Universiti Technologi Malaysia (UTM) (9)

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

Recently uploaded

Digital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxDigital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxLoriGlavin3
 
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024BookNet Canada
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxNavinnSomaal
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupFlorian Wilhelm
 
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxThe Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxLoriGlavin3
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsPixlogix Infotech
 
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxMerck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxLoriGlavin3
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 3652toLead Limited
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity PlanDatabarracks
 
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteDianaGray10
 
Generative AI for Technical Writer or Information Developers
Generative AI for Technical Writer or Information DevelopersGenerative AI for Technical Writer or Information Developers
Generative AI for Technical Writer or Information DevelopersRaghuram Pandurangan
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsRizwan Syed
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLScyllaDB
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek SchlawackFwdays
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 
The State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptxThe State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptxLoriGlavin3
 
Advanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionAdvanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionDilum Bandara
 

Recently uploaded (20)

Digital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxDigital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
 
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptx
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project Setup
 
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxThe Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and Cons
 
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxMerck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity Plan
 
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test Suite
 
Generative AI for Technical Writer or Information Developers
Generative AI for Technical Writer or Information DevelopersGenerative AI for Technical Writer or Information Developers
Generative AI for Technical Writer or Information Developers
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL Certs
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQL
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 
The State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptxThe State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptx
 
Advanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionAdvanced Computer Architecture – An Introduction
Advanced Computer Architecture – An Introduction
 

Recommender Systems Explained: Research on Using Explanations

  • 1. EXPLANATIONS IN RECOMMENDER SYSTEMS Overview And Research Approaches Mohammed Zuhair Al-Taie AL-Salam University College -- Iraq – Email: mza004@live.aul.edu.lb This study was published in “The International Arab This study was published in “The International Arab Conference on Information Technology (ACIT)” December Conference on Information Technology (ACIT)” December -2013 -2013
  • 2. Goal of the study  The goal of this study to survey & comprehend the main streams of research in the field of Explanations in Recommender Systems and put them in one integral work.  It starts by explaining the main concepts of the field and then moves on to present and discuss the various sub-topics that took much interest from researchers. 2
  • 3. 3
  • 4. What Are Recommender System (RS)?  Also called Recommendation Systems, they are software tools and techniques providing suggestions for items to be of use to a user. Benefits  RS are being well used in various application domains such as music, videos, queries, news, friends on social networks etc.. 4
  • 6. Explanations in Recommender System  Important pieces of information that are used by both selling and buying agents, through their communication process, to increase their performance.  Another definition … it is a description that makes users better realize if the recommended item is relevant to their needs or not 6
  • 7. Explanations - Examples YouTube Explanation System AR estaurant Recommendation Explanation 7
  • 10. Phrases Expressing Explanations  More on this artist …  Try something from similar artists …  Someone similar to you also like this …  As you listened to that, you may want this …  These two go together …  This is highly rated …  Try something new …  Similar or related products  Complementary accessories ...  Gift idea ...  Welcome back (recently viewed) …  For you today …  New for you …  Hot / Most popular of this type …  Other people also do this … … 10
  • 11. Explanations – A Short History  The importance of explanations has been well identified in pervious paradigms such as Expert Systems.  Due to the decline of studies in Expert Systems in the 1990s, Recommender Systems borrowed the concepts of explanations.  A seminal study by Herlocker et al. in 2000 on explanations in RS, which stated that recommender systems had worked as black boxes, lead the body of research in explanations to grow. 11
  • 12. …However  There are many types of explanations and various goals they can achieve.  Goals such as: effectiveness, efficiency, transparency, trustworthiness, validity.. can not all be achieved in one system at one time. Therefore, a deep understanding of explanations and their effects on customers is of great importance. 12
  • 13. Types of explanations in RS  Different criteria to classify explanations … 13
  • 14. RS Explanation Styles  Explanation styles are related to the methods used to generate explanations.  The most commonly-used explanation styles are: 14
  • 15. 15
  • 16. Research Approaches in Explanations  Researchers spread their efforts across different research aspects. Generally, they can be divided into two approaches: 16
  • 17. Explanations Attributes (Goals)  Explanation attributes are the benefits that explanations give to recommender systems. These benefits fall into the following 11 aims: 17
  • 18. .(Explanations Attributes (Cont Transparency- 1 Provide information so the user can comprehend the reasoning used to generate a specific recommendation Validity- 2 Allow a user to check the validity of a recommendation Trustworthiness- 3 A mechanism for reducing the complexity of human decision making in uncertain situations Persuasiveness- 4 Persuasive explanations for recommendations aim to change the user's buying behavior. E.g., a recommender may intentionally dwell on a product's positive aspects and keep quiet about various negative aspects 18
  • 19. .(Explanations Attributes (Cont Scrutability- 5 means that users can tell if the system is wrong Effectiveness- 6 Help users make better decisions Efficiency- 7 Reduce the decision-making effort Reduce the time needed for decision making Satisfaction- 8 Improve the overall satisfaction stemming from the use of a recommender system Relevance- 9 Explanations can be provided to justify why additional information is needed from the user 19
  • 20. .(Explanations Attributes (Cont Comprehensibility- 10 Recommenders can never be sure about the knowledge of their users. Therefore explanations support the user by relating the user's known concepts to the concepts employed by the recommender Education- 11 Educate users to help them better understand the product domain. So, as customers become more informed, they are able to make wiser purchasing decisions 20
  • 21. Other Research Directions Other than explanation attributes, researchers are investigating a number of different approaches. Among them are the following three important fields: 1. Explanation Interfaces 2. Decision Making 3. Over and Under Estimation 21
  • 22. Explanation Interfaces( 1  Explanation Interface is the technique used to control the format by which explanations are presented to a user (meaning that how explanations are shown to users). Motives:  The importance of a good interface is that it can better explain recommendations and can even push users to make further requests.  The use of modalities such as text, graphs, tables, images and colors can better present explanations to users. For example: 22
  • 24. Over and Underestimation( 3 Over and Underestimation: overestimation means that users may try a product they do not end up liking. underestimation means that users miss products they might have appreciated Motives: Overestimation may lead users later on to distrust the system after discovering that the items it recommended were not that useful. On the other hand under estimation may make users miss items that fitted their interests and eventually make them distrust the system. 24
  • 25. Open Challenges A number of challenges are still waiting to be probed by people working in the field: 25