SlideShare a Scribd company logo
Motiv. Def. Desi. Impl. Conclu. Biblio.
Bayesian Networks to Predict Reputation in
Virtual Learning Communities
Luis Chamba-Eras A, B
Ana Arruarte and Jon Ander Elorriaga B
A Carrera de Ingenier´ıa en Sistemas - Universidad Nacional de Loja (UNL),
Ecuador
B Computer Languages and Systems Department - University of the Basque
Country (UPV/EHU), Ga-Lan Group, Spain
”2016 IEEE Latin American Conference on Computational Intelligence”
Cartagena-Colombia: 2-4 November 2016
1 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Outline
Motivations
Definitions and related work
Design of the Bayesian Network
Implementation of prototype
Conclusions and future work
Bibliography
2 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Outline
Motivations
Definitions and related work
Design of the Bayesian Network
Implementation of prototype
Conclusions and future work
Bibliography
3 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Motivations
• With the Internet Of Things and the support given by the In-
formation and Communication Technologies, real time partic-
ipation and collaboration between individuals in different geo-
graphical locations is a reality in e-learning.
• Currently there is great interest in predicting the indirect trust
or reputation among members of a Virtual Learning Commu-
nities (VLC): students and teachers. Any trust and reputation
model have been implemented in the field of education, partic-
ularly in the VLC using aggregation algorithms, to estimate the
capture of previous interactions of the members on resources
or activities value reputation.
4 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
This is the reality!
• ”I like” or ”I don’t like”
Figure 1: Sites that implement social computing
5 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Outline
Motivations
Definitions and related work
Design of the Bayesian Network
Implementation of prototype
Conclusions and future work
Bibliography
6 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Preliminary concepts
• Bayesian Networks (BN), known as probabilistic models or be-
lief networks, have been investigated due to a growing interest
in predicting future events, a BN in general is a relationships
network that uses statistical methods to represent probability
relationships between different nodes. It is a compact repre-
sentation of the joint probability distribution to reason under
uncertainty.
• Virtual Learning Communities (VLC), enabling members to pro-
duce knowledge, resulting from social interaction in a collabo-
rative learning process.
• Trust, concept is complex, so there are multiple definitions in
different contexts, initially, it was defined as the extent to which
an individual has confidence and is willing to interact with some-
one based on words, actions and decisions of others.
7 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Preliminary concepts
• Reputation, it is defined as the opinion that someone has about
something or somebody collected through indirect experiences.
The reputation of a member of a VLC is the opinion that other
members have on him. This opinion is based on the record of
positive and negative interactions executed by them.
• Positive reinforcement, is the reward offered to the member of
the VLC after performing a desired behavior, thereby determin-
ing the presence of this reward increases the probability that a
behavior will occur.
• Negative reinforcement, is the result offered to the member
after the appearance of unwanted conduct.
8 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Preliminary concepts
• Online reputation, mid systems and unmediated. The mid sys-
tems, from simple systems are the spaces type of review of
consumers using aggregation algorithms, for example as type
consumer review sites: Yelp, Amazon, eBay, TripAdvisor, Re-
alSelf.com, Menelaus, IMD, among others, or, to complex sys-
tems ratings as Moody. The unmediated systems are those in
which the information provided by community members flows
freely between all of them while mid systems needs a third agent
that collects, stores, organizes and publishes. Examples of not
mediated systems are recommendation letters such as those in
LinkedIn, StackOverflow, reports Infojob, word of mouth net-
works such as Facebook or forums.
9 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Related work
Related work combining BN, trust and reputation:
• Trang Nguye et al.
• L´opez-Faican et al.
• Daniel et al.
• Qi et al.
• Li et al.
• Jøsang et al.
• Patel et al.
• Aciar et al.
10 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Outline
Motivations
Definitions and related work
Design of the Bayesian Network
Implementation of prototype
Conclusions and future work
Bibliography
11 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Previous definitions
Figure 2: Acronyms of the context
12 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Factors: direct experience and reputation
• Direct experience (F1): it is based on satisfaction concept and
it is a critical factor. Direct experience is obtained interact-
ing with the ISs in the VLC. This is not always equal since in
every society there are different points of view. An aggrega-
tion algorithm adapted to the VLC area, calculates the direct
experience considering the interaction of members of the VLC
with resources and learning activities managed in an LMS. Con-
cretely, the algorithm considers the ”I like” actions (positive
reinforcement) and ”I don’t like” actions (negative reinforce-
ment) that each member performs on the resources/activities
used and managed by the LMS.
13 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Factors: direct experience and reputation
• Reputation (F2): in our proposal reputation factor (F2) is cal-
culated from past interactions achieved through direct experi-
ence (F1) between ISs in the VLC. The reputation of a member
is the opinion that the other members have on him. This opin-
ion is based on the history of positive and negative interactions
carried out by them. People trust more in those individuals
that have higher affinity. This factor is useful when there is
little previous direct experience between the IS in the VLC.
14 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Bayesian Network Model
Figure 3: BN factor by reputation of the TM
15 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Formalization Bayesian Network
Bayes Theorem:
Figure 4: Bayes Theorem
16 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Formalization Bayesian Network
Initial training values: estimates for positive/negative reputation
Figure 5: Training values BN
17 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Formalization Bayesian Network
Initial training values: positive reputation estimated values
Figure 6: Positive reputation estimated values
18 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Formalization Bayesian Network
Initial training values: negative reputation estimated values
Figure 7: Negative reputation estimated values
19 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Formalization Bayesian Network
BN obtains for each member the probability of positive and negative
reputation.
Figure 8: Estimation of positive and negative reputation for individual
member in VLC
20 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Outline
Motivations
Definitions and related work
Design of the Bayesian Network
Implementation of prototype
Conclusions and future work
Bibliography
21 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Implementation details in Moodle
• LMS Moodle 2.8.2.
• Moodle Core, new modules and plugins.
• Implement the direct experience and reputation.
• Show resources: https://goo.gl/dOd6gO
22 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Implementation details in Moodle
The prototype enables two options ”I like” or ”I don’t like” on the LA
and LR, which will be evaluated by each member based objectively
on the contribution of these to their learning.
Figure 9: Implementation of ”I like” or ”I don’t like” in the forum activity
by direct experience
23 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Implementation details in Moodle
When the member is on the VLC the ”trustmodel” block presents
summary information of the scores that the member has achieved.
Figure 10: Trust data based on the TM for each member in the VLC by
reputation
24 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Using real scenario in VLC
The prototype in real scenario for VLC, the process was as follows:
1. Start and management the virtual community for learning ”Math-
ematical Software” in Web.
2. 24 members enrolled in VLC, two teachers and 22 students.
3. Teachers tutoring and sharing activities/resources in VLC for
two month.
4. Interaction and participate with members in VLC.
5. Recollected dataset about reputation factor in prototype using
the ”trustmodel” block.
6. Comparison the dataset with the BN training values implement
in BayesiaLab.
25 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Using real scenario in VLC
The values calculated by positive reputation compared to estimates
reputation using the BN with the software BayesiaLab, identified
that there are small differences between the values calculated with
the prototype and BayesiaLab.
Figure 11: Comparative reputation result
26 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Outline
Motivations
Definitions and related work
Design of the Bayesian Network
Implementation of prototype
Conclusions and future work
Bibliography
27 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Conclusions and future work
• The main contributions of this paper are the development and
implement the BN for predicting reputation of members of VLC.
• In this paper, we present the design of a BN that predicts repu-
tation from past interactions achieved through direct experience
between members of a VLC. It has been implemented in the
Moodle LMS.
• In the work presented here the eBay aggregation algorithm
adapted to the VLC area has been implemented. It calculates
the direct experience considering the interaction of members
of the VLC with resources and learning activities managed in
the Moodle. The algorithm considers the behavioral Psychol-
ogy with ”I like” actions as positive reinforcement and ”I don’t
like” actions as negative reinforcement.
28 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Conclusions and future work
• In our work the past interaction is gathered from direct experi-
ence factor and use to predict value reputation factor.
• As future work, consider the views of members with different
features present in a VLC and combining the BN with other Ar-
tificial Intelligence techniques as Natural Language Processing
to identify through forums reputation.
29 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Outline
Motivations
Definitions and related work
Design of the Bayesian Network
Implementation of prototype
Conclusions and future work
Bibliography
30 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
Bibliography
• Aguilar, J. (2015). Confianza y reputaci´on en Sistemas Multi-Agentes.
Universidad de los Andes.
• Chamba-Eras, L. (2011). Modelo de Confianza para Objetos de
Aprendizaje en Comunidades Virtuales. Master Thesis. Universidad
del Pa´ıs Vasco.
• Esfandiari, B. and Chandrasekharan, S. (2001). On how agents make
friends: Mechanisms for trust acquisition. In Proceedings of the
Fourth Workshop on Deception, Fraud and Trust in Agent Societies,
pages 27-34, Montreal, Canada.
• Gambetta, D. (1990). Trust: Making and Breaking Cooperative Rela-
tions, chapter Can We Trust Trust?, pages 213-237. Basil Blackwell,
Oxford.
• Garc´ıa, A. (Ed.), Ruiz, C. y Dom´ınguez, F. (2007). De la educaci´on
a distancia a la educaci´on virtual. Barcelona: Ariel.
31 / 32
Motiv. Def. Desi. Impl. Conclu. Biblio.
(Creative Commons) BY-NC-SA
Thanks,
Researchers: Luis Chamba-Eras, Ana Arruarte and Jon A. Elorriaga
email: lachamba@unl.edu.ec, a.arruarte@ehu.eus, jon.elorriaga@ehu.eus
Research Group: Ga-Lan, http://galan.ehu.es
Twitter: @lachamba
32 / 32

More Related Content

PPT
Overview Of Network Analysis Platforms
PPTX
Roles In Networks
PPTX
Social Network Analysis Workshop
PPTX
Social Network Analysis: applications for education research
PDF
Recommender systems in the scope of opinion formation: a model
PDF
DeLiddo&BuckinghamShum-e-Part2014
PPT
Montreal Extras
PDF
Places for News: an exploration of context and situated methods
Overview Of Network Analysis Platforms
Roles In Networks
Social Network Analysis Workshop
Social Network Analysis: applications for education research
Recommender systems in the scope of opinion formation: a model
DeLiddo&BuckinghamShum-e-Part2014
Montreal Extras
Places for News: an exploration of context and situated methods

What's hot (20)

PPTX
Defense
PDF
Multilevel Collaboration between Software Developers and the Impact of Proxim...
PDF
LAK13 Tutorial Social Network Analysis 4 Learning Analytics
PDF
Social Network Analysis & an Introduction to Tools
PDF
Introduction to Social Network Analysis
PPT
Social Network Analysis
PPT
How to conduct a social network analysis: A tool for empowering teams and wor...
PPTX
A Guide to Social Network Analysis
PPTX
A Community of Quality: Using Social Network Analysis to Study University-Wid...
PDF
Introduction to Social Network Analysis
PPT
2009 Node XL Overview: Social Network Analysis in Excel 2007
PPTX
Visualizing Community through Social Network Analysis
PPT
PhD Defense - A Context Management Framework based on Wisdom of Crowds for So...
PDF
2009-Social computing-First steps to netviz nirvana
PPT
Activating Online Collaborative Communities
PPTX
Mining and analyzing social media part 2 - hicss47 tutorial - dave king
PPT
Personalizing the web building effective recommender systems
PPTX
Social Network Analysis: What It Is, Why We Should Care, and What We Can Lear...
PPTX
Analysis of Overlapping Communities in Signed Complex Networks
Defense
Multilevel Collaboration between Software Developers and the Impact of Proxim...
LAK13 Tutorial Social Network Analysis 4 Learning Analytics
Social Network Analysis & an Introduction to Tools
Introduction to Social Network Analysis
Social Network Analysis
How to conduct a social network analysis: A tool for empowering teams and wor...
A Guide to Social Network Analysis
A Community of Quality: Using Social Network Analysis to Study University-Wid...
Introduction to Social Network Analysis
2009 Node XL Overview: Social Network Analysis in Excel 2007
Visualizing Community through Social Network Analysis
PhD Defense - A Context Management Framework based on Wisdom of Crowds for So...
2009-Social computing-First steps to netviz nirvana
Activating Online Collaborative Communities
Mining and analyzing social media part 2 - hicss47 tutorial - dave king
Personalizing the web building effective recommender systems
Social Network Analysis: What It Is, Why We Should Care, and What We Can Lear...
Analysis of Overlapping Communities in Signed Complex Networks
Ad

Similar to Bayesian Networks to Predict Reputation in Virtual Learning Communities (20)

PDF
Learning Analytics BETT2013
PDF
2015-11-11 research seminar
PPT
CFMC NWLC 20100902
PPTX
Graph Neural Networks for Social Recommendation.pptx
PDF
Fundamentals of Deep Recommender Systems
PPT
Design challenges for future learning
PPT
sm@jgc Session Three
PDF
A Learner-Centred Approach for Lifelong Learning Powered by the Blockchain. M...
PDF
Designing Problem Based Learning Online
PDF
Global Redirective Practices: an online workshop for a client
PDF
ONA and the tools landscape
PPT
Aera CVLE presentation
PPT
CFMC NWLC 20101021
PDF
User behavior model & recommendation on basis of social networks
PDF
Who will follow whom? Exploiting Semantics for Link Prediction in Attention-I...
PDF
The role of online social networks in inter-firm collaborative innovation and...
PPT
Co-creation of Learning and Social CRM
PPT
Global Redirective Practices
ODP
Designing and using group software through patterns
DOCX
ME290 Global Engineering Professional Seminar Knowl.docx
Learning Analytics BETT2013
2015-11-11 research seminar
CFMC NWLC 20100902
Graph Neural Networks for Social Recommendation.pptx
Fundamentals of Deep Recommender Systems
Design challenges for future learning
sm@jgc Session Three
A Learner-Centred Approach for Lifelong Learning Powered by the Blockchain. M...
Designing Problem Based Learning Online
Global Redirective Practices: an online workshop for a client
ONA and the tools landscape
Aera CVLE presentation
CFMC NWLC 20101021
User behavior model & recommendation on basis of social networks
Who will follow whom? Exploiting Semantics for Link Prediction in Attention-I...
The role of online social networks in inter-firm collaborative innovation and...
Co-creation of Learning and Social CRM
Global Redirective Practices
Designing and using group software through patterns
ME290 Global Engineering Professional Seminar Knowl.docx
Ad

More from Universidad Nacional de Loja (20)

PDF
Democratización del aprendizaje de la inteligencia artificial desde edades te...
PDF
¿Dónde publicar?
PDF
Clase3 - Metodología de la Investigación en Ciencias de la Computación: Intro...
PDF
Clase 2- Introducción a los Proyectos Informáticos
PDF
Clase1- Introducción a la Gestión de Proyectos Informáticos
PDF
Clase1- Introducción a los Proyectos Informáticos
PDF
Encuadre de la Asignatura de Proyectos Informáticos II - abril-septiembre 2020
PDF
Encuadre de la Asignatura de Proyectos Informáticos I - abril-septiembre 2020
PDF
Encuadre de la Asignatura de Inteligencia Artificial - abril-septiembre 2020
PDF
Metodologías, recursos, y recomendaciones prácticas para preparar un curso en...
PPTX
Rol del Tutor en el proceso de enseñanza-aprendizaje eLearning
PDF
Machine Learning para Wawas
PDF
Inteligencia Artificial en la Educación: Machine Learning y Scratch 3.0
PDF
Cienciometria y desarrollo de colecciones
PDF
La Tecnología en las Tendencias de Innovación Educativa: Aprendizaje mediado ...
PDF
MDE para identificar la relación entre el IQ, IM, EA, IE de estudiantes de in...
PDF
MDE para identificar la relación de IQ, IM, EA, IE de estudiantes de ingeniería
PDF
Curso Ciencia 2.0: Recursos para aprendizaje, investigación e innovación
PDF
Curso Ciencia 2.0: Recursos para el docente universitario
PDF
Curso Ciencia 2.0: NMC Horizon Report 2017
Democratización del aprendizaje de la inteligencia artificial desde edades te...
¿Dónde publicar?
Clase3 - Metodología de la Investigación en Ciencias de la Computación: Intro...
Clase 2- Introducción a los Proyectos Informáticos
Clase1- Introducción a la Gestión de Proyectos Informáticos
Clase1- Introducción a los Proyectos Informáticos
Encuadre de la Asignatura de Proyectos Informáticos II - abril-septiembre 2020
Encuadre de la Asignatura de Proyectos Informáticos I - abril-septiembre 2020
Encuadre de la Asignatura de Inteligencia Artificial - abril-septiembre 2020
Metodologías, recursos, y recomendaciones prácticas para preparar un curso en...
Rol del Tutor en el proceso de enseñanza-aprendizaje eLearning
Machine Learning para Wawas
Inteligencia Artificial en la Educación: Machine Learning y Scratch 3.0
Cienciometria y desarrollo de colecciones
La Tecnología en las Tendencias de Innovación Educativa: Aprendizaje mediado ...
MDE para identificar la relación entre el IQ, IM, EA, IE de estudiantes de in...
MDE para identificar la relación de IQ, IM, EA, IE de estudiantes de ingeniería
Curso Ciencia 2.0: Recursos para aprendizaje, investigación e innovación
Curso Ciencia 2.0: Recursos para el docente universitario
Curso Ciencia 2.0: NMC Horizon Report 2017

Recently uploaded (20)

PDF
A GUIDE TO GENETICS FOR UNDERGRADUATE MEDICAL STUDENTS
PDF
The Lost Whites of Pakistan by Jahanzaib Mughal.pdf
PDF
What if we spent less time fighting change, and more time building what’s rig...
PPTX
PPT- ENG7_QUARTER1_LESSON1_WEEK1. IMAGERY -DESCRIPTIONS pptx.pptx
PDF
Paper A Mock Exam 9_ Attempt review.pdf.
PDF
Updated Idioms and Phrasal Verbs in English subject
PPTX
Orientation - ARALprogram of Deped to the Parents.pptx
PDF
grade 11-chemistry_fetena_net_5883.pdf teacher guide for all student
PDF
Microbial disease of the cardiovascular and lymphatic systems
PDF
Black Hat USA 2025 - Micro ICS Summit - ICS/OT Threat Landscape
PPTX
Final Presentation General Medicine 03-08-2024.pptx
PPTX
Introduction-to-Literarature-and-Literary-Studies-week-Prelim-coverage.pptx
PDF
LDMMIA Reiki Yoga Finals Review Spring Summer
PPTX
History, Philosophy and sociology of education (1).pptx
PDF
Classroom Observation Tools for Teachers
PDF
ChatGPT for Dummies - Pam Baker Ccesa007.pdf
PPTX
school management -TNTEU- B.Ed., Semester II Unit 1.pptx
PDF
LNK 2025 (2).pdf MWEHEHEHEHEHEHEHEHEHEHE
PDF
Trump Administration's workforce development strategy
PDF
GENETICS IN BIOLOGY IN SECONDARY LEVEL FORM 3
A GUIDE TO GENETICS FOR UNDERGRADUATE MEDICAL STUDENTS
The Lost Whites of Pakistan by Jahanzaib Mughal.pdf
What if we spent less time fighting change, and more time building what’s rig...
PPT- ENG7_QUARTER1_LESSON1_WEEK1. IMAGERY -DESCRIPTIONS pptx.pptx
Paper A Mock Exam 9_ Attempt review.pdf.
Updated Idioms and Phrasal Verbs in English subject
Orientation - ARALprogram of Deped to the Parents.pptx
grade 11-chemistry_fetena_net_5883.pdf teacher guide for all student
Microbial disease of the cardiovascular and lymphatic systems
Black Hat USA 2025 - Micro ICS Summit - ICS/OT Threat Landscape
Final Presentation General Medicine 03-08-2024.pptx
Introduction-to-Literarature-and-Literary-Studies-week-Prelim-coverage.pptx
LDMMIA Reiki Yoga Finals Review Spring Summer
History, Philosophy and sociology of education (1).pptx
Classroom Observation Tools for Teachers
ChatGPT for Dummies - Pam Baker Ccesa007.pdf
school management -TNTEU- B.Ed., Semester II Unit 1.pptx
LNK 2025 (2).pdf MWEHEHEHEHEHEHEHEHEHEHE
Trump Administration's workforce development strategy
GENETICS IN BIOLOGY IN SECONDARY LEVEL FORM 3

Bayesian Networks to Predict Reputation in Virtual Learning Communities

  • 1. Motiv. Def. Desi. Impl. Conclu. Biblio. Bayesian Networks to Predict Reputation in Virtual Learning Communities Luis Chamba-Eras A, B Ana Arruarte and Jon Ander Elorriaga B A Carrera de Ingenier´ıa en Sistemas - Universidad Nacional de Loja (UNL), Ecuador B Computer Languages and Systems Department - University of the Basque Country (UPV/EHU), Ga-Lan Group, Spain ”2016 IEEE Latin American Conference on Computational Intelligence” Cartagena-Colombia: 2-4 November 2016 1 / 32
  • 2. Motiv. Def. Desi. Impl. Conclu. Biblio. Outline Motivations Definitions and related work Design of the Bayesian Network Implementation of prototype Conclusions and future work Bibliography 2 / 32
  • 3. Motiv. Def. Desi. Impl. Conclu. Biblio. Outline Motivations Definitions and related work Design of the Bayesian Network Implementation of prototype Conclusions and future work Bibliography 3 / 32
  • 4. Motiv. Def. Desi. Impl. Conclu. Biblio. Motivations • With the Internet Of Things and the support given by the In- formation and Communication Technologies, real time partic- ipation and collaboration between individuals in different geo- graphical locations is a reality in e-learning. • Currently there is great interest in predicting the indirect trust or reputation among members of a Virtual Learning Commu- nities (VLC): students and teachers. Any trust and reputation model have been implemented in the field of education, partic- ularly in the VLC using aggregation algorithms, to estimate the capture of previous interactions of the members on resources or activities value reputation. 4 / 32
  • 5. Motiv. Def. Desi. Impl. Conclu. Biblio. This is the reality! • ”I like” or ”I don’t like” Figure 1: Sites that implement social computing 5 / 32
  • 6. Motiv. Def. Desi. Impl. Conclu. Biblio. Outline Motivations Definitions and related work Design of the Bayesian Network Implementation of prototype Conclusions and future work Bibliography 6 / 32
  • 7. Motiv. Def. Desi. Impl. Conclu. Biblio. Preliminary concepts • Bayesian Networks (BN), known as probabilistic models or be- lief networks, have been investigated due to a growing interest in predicting future events, a BN in general is a relationships network that uses statistical methods to represent probability relationships between different nodes. It is a compact repre- sentation of the joint probability distribution to reason under uncertainty. • Virtual Learning Communities (VLC), enabling members to pro- duce knowledge, resulting from social interaction in a collabo- rative learning process. • Trust, concept is complex, so there are multiple definitions in different contexts, initially, it was defined as the extent to which an individual has confidence and is willing to interact with some- one based on words, actions and decisions of others. 7 / 32
  • 8. Motiv. Def. Desi. Impl. Conclu. Biblio. Preliminary concepts • Reputation, it is defined as the opinion that someone has about something or somebody collected through indirect experiences. The reputation of a member of a VLC is the opinion that other members have on him. This opinion is based on the record of positive and negative interactions executed by them. • Positive reinforcement, is the reward offered to the member of the VLC after performing a desired behavior, thereby determin- ing the presence of this reward increases the probability that a behavior will occur. • Negative reinforcement, is the result offered to the member after the appearance of unwanted conduct. 8 / 32
  • 9. Motiv. Def. Desi. Impl. Conclu. Biblio. Preliminary concepts • Online reputation, mid systems and unmediated. The mid sys- tems, from simple systems are the spaces type of review of consumers using aggregation algorithms, for example as type consumer review sites: Yelp, Amazon, eBay, TripAdvisor, Re- alSelf.com, Menelaus, IMD, among others, or, to complex sys- tems ratings as Moody. The unmediated systems are those in which the information provided by community members flows freely between all of them while mid systems needs a third agent that collects, stores, organizes and publishes. Examples of not mediated systems are recommendation letters such as those in LinkedIn, StackOverflow, reports Infojob, word of mouth net- works such as Facebook or forums. 9 / 32
  • 10. Motiv. Def. Desi. Impl. Conclu. Biblio. Related work Related work combining BN, trust and reputation: • Trang Nguye et al. • L´opez-Faican et al. • Daniel et al. • Qi et al. • Li et al. • Jøsang et al. • Patel et al. • Aciar et al. 10 / 32
  • 11. Motiv. Def. Desi. Impl. Conclu. Biblio. Outline Motivations Definitions and related work Design of the Bayesian Network Implementation of prototype Conclusions and future work Bibliography 11 / 32
  • 12. Motiv. Def. Desi. Impl. Conclu. Biblio. Previous definitions Figure 2: Acronyms of the context 12 / 32
  • 13. Motiv. Def. Desi. Impl. Conclu. Biblio. Factors: direct experience and reputation • Direct experience (F1): it is based on satisfaction concept and it is a critical factor. Direct experience is obtained interact- ing with the ISs in the VLC. This is not always equal since in every society there are different points of view. An aggrega- tion algorithm adapted to the VLC area, calculates the direct experience considering the interaction of members of the VLC with resources and learning activities managed in an LMS. Con- cretely, the algorithm considers the ”I like” actions (positive reinforcement) and ”I don’t like” actions (negative reinforce- ment) that each member performs on the resources/activities used and managed by the LMS. 13 / 32
  • 14. Motiv. Def. Desi. Impl. Conclu. Biblio. Factors: direct experience and reputation • Reputation (F2): in our proposal reputation factor (F2) is cal- culated from past interactions achieved through direct experi- ence (F1) between ISs in the VLC. The reputation of a member is the opinion that the other members have on him. This opin- ion is based on the history of positive and negative interactions carried out by them. People trust more in those individuals that have higher affinity. This factor is useful when there is little previous direct experience between the IS in the VLC. 14 / 32
  • 15. Motiv. Def. Desi. Impl. Conclu. Biblio. Bayesian Network Model Figure 3: BN factor by reputation of the TM 15 / 32
  • 16. Motiv. Def. Desi. Impl. Conclu. Biblio. Formalization Bayesian Network Bayes Theorem: Figure 4: Bayes Theorem 16 / 32
  • 17. Motiv. Def. Desi. Impl. Conclu. Biblio. Formalization Bayesian Network Initial training values: estimates for positive/negative reputation Figure 5: Training values BN 17 / 32
  • 18. Motiv. Def. Desi. Impl. Conclu. Biblio. Formalization Bayesian Network Initial training values: positive reputation estimated values Figure 6: Positive reputation estimated values 18 / 32
  • 19. Motiv. Def. Desi. Impl. Conclu. Biblio. Formalization Bayesian Network Initial training values: negative reputation estimated values Figure 7: Negative reputation estimated values 19 / 32
  • 20. Motiv. Def. Desi. Impl. Conclu. Biblio. Formalization Bayesian Network BN obtains for each member the probability of positive and negative reputation. Figure 8: Estimation of positive and negative reputation for individual member in VLC 20 / 32
  • 21. Motiv. Def. Desi. Impl. Conclu. Biblio. Outline Motivations Definitions and related work Design of the Bayesian Network Implementation of prototype Conclusions and future work Bibliography 21 / 32
  • 22. Motiv. Def. Desi. Impl. Conclu. Biblio. Implementation details in Moodle • LMS Moodle 2.8.2. • Moodle Core, new modules and plugins. • Implement the direct experience and reputation. • Show resources: https://goo.gl/dOd6gO 22 / 32
  • 23. Motiv. Def. Desi. Impl. Conclu. Biblio. Implementation details in Moodle The prototype enables two options ”I like” or ”I don’t like” on the LA and LR, which will be evaluated by each member based objectively on the contribution of these to their learning. Figure 9: Implementation of ”I like” or ”I don’t like” in the forum activity by direct experience 23 / 32
  • 24. Motiv. Def. Desi. Impl. Conclu. Biblio. Implementation details in Moodle When the member is on the VLC the ”trustmodel” block presents summary information of the scores that the member has achieved. Figure 10: Trust data based on the TM for each member in the VLC by reputation 24 / 32
  • 25. Motiv. Def. Desi. Impl. Conclu. Biblio. Using real scenario in VLC The prototype in real scenario for VLC, the process was as follows: 1. Start and management the virtual community for learning ”Math- ematical Software” in Web. 2. 24 members enrolled in VLC, two teachers and 22 students. 3. Teachers tutoring and sharing activities/resources in VLC for two month. 4. Interaction and participate with members in VLC. 5. Recollected dataset about reputation factor in prototype using the ”trustmodel” block. 6. Comparison the dataset with the BN training values implement in BayesiaLab. 25 / 32
  • 26. Motiv. Def. Desi. Impl. Conclu. Biblio. Using real scenario in VLC The values calculated by positive reputation compared to estimates reputation using the BN with the software BayesiaLab, identified that there are small differences between the values calculated with the prototype and BayesiaLab. Figure 11: Comparative reputation result 26 / 32
  • 27. Motiv. Def. Desi. Impl. Conclu. Biblio. Outline Motivations Definitions and related work Design of the Bayesian Network Implementation of prototype Conclusions and future work Bibliography 27 / 32
  • 28. Motiv. Def. Desi. Impl. Conclu. Biblio. Conclusions and future work • The main contributions of this paper are the development and implement the BN for predicting reputation of members of VLC. • In this paper, we present the design of a BN that predicts repu- tation from past interactions achieved through direct experience between members of a VLC. It has been implemented in the Moodle LMS. • In the work presented here the eBay aggregation algorithm adapted to the VLC area has been implemented. It calculates the direct experience considering the interaction of members of the VLC with resources and learning activities managed in the Moodle. The algorithm considers the behavioral Psychol- ogy with ”I like” actions as positive reinforcement and ”I don’t like” actions as negative reinforcement. 28 / 32
  • 29. Motiv. Def. Desi. Impl. Conclu. Biblio. Conclusions and future work • In our work the past interaction is gathered from direct experi- ence factor and use to predict value reputation factor. • As future work, consider the views of members with different features present in a VLC and combining the BN with other Ar- tificial Intelligence techniques as Natural Language Processing to identify through forums reputation. 29 / 32
  • 30. Motiv. Def. Desi. Impl. Conclu. Biblio. Outline Motivations Definitions and related work Design of the Bayesian Network Implementation of prototype Conclusions and future work Bibliography 30 / 32
  • 31. Motiv. Def. Desi. Impl. Conclu. Biblio. Bibliography • Aguilar, J. (2015). Confianza y reputaci´on en Sistemas Multi-Agentes. Universidad de los Andes. • Chamba-Eras, L. (2011). Modelo de Confianza para Objetos de Aprendizaje en Comunidades Virtuales. Master Thesis. Universidad del Pa´ıs Vasco. • Esfandiari, B. and Chandrasekharan, S. (2001). On how agents make friends: Mechanisms for trust acquisition. In Proceedings of the Fourth Workshop on Deception, Fraud and Trust in Agent Societies, pages 27-34, Montreal, Canada. • Gambetta, D. (1990). Trust: Making and Breaking Cooperative Rela- tions, chapter Can We Trust Trust?, pages 213-237. Basil Blackwell, Oxford. • Garc´ıa, A. (Ed.), Ruiz, C. y Dom´ınguez, F. (2007). De la educaci´on a distancia a la educaci´on virtual. Barcelona: Ariel. 31 / 32
  • 32. Motiv. Def. Desi. Impl. Conclu. Biblio. (Creative Commons) BY-NC-SA Thanks, Researchers: Luis Chamba-Eras, Ana Arruarte and Jon A. Elorriaga email: lachamba@unl.edu.ec, a.arruarte@ehu.eus, jon.elorriaga@ehu.eus Research Group: Ga-Lan, http://galan.ehu.es Twitter: @lachamba 32 / 32