the use of emotions in student assessment in a virtual ... [sala4 w... · the use of emotions in...
TRANSCRIPT
PROGRAMA DE PÓS-GRADUAÇÃO EM SISTEMAS E
PROCESSOS INDUSTRIAIS - MESTRADO
The use of Emotions in Student Assessment in a Virtual
Learning Environment
Nadiesca Homrich Scherer
Jacques Nelson Corleta Schreiber
Rejane Frozza
Liane Mahlmann Kipper (Lecturer)
Santa Cruz do Sul University
POST-GRADUATION PROGRAM IN INDUSTRIAL SYSTEMS
AND PROCESSES - MASTERS
The use of Emotions in Student Assessment
in a Virtual Learning Environment
Nadiesca Homrich Scherer
Prof. Jacques Nelson Corleta Schreiber
Prof. Rejane Frozza
Prof. Liane Mahlmann Kipper (Lecturer)
University of Santa Cruz do Sul
Liane Mahlmann Kipper
Summary
3
1. Introduction
2. Objectives
3. Theoretical Foundation
4. Method of Inference and VLE
5. Methodology
6. Conclusion
7. References
Introduction
• In distance learning, teachers and students
communicate and interact through a Virtual Learning
Environment (VLE).
• Knowing the student's emotions during the access to
VLE may support the improvement of the quality of
interaction.
Liane Mahlmann Kipper 4
In the learning process there is a relationship between cognition
and emotion.
•Longhi et al (2007), say "affection may assist in reasoning.“
•Piaget (1983) says "Surely affectivity or its deprivation may be
the cause of acceleration or delay in cognitive development.“
•Picard et al. (2004) talk about the tendency to see the
computer as a learning "motivator" by making use of emotions
for better interaction.
Introduction
Liane Mahlmann Kipper 5
Therefore, it is possible to see the importance of
studies in the relationship between cognition and
emotion in VLE.
Introduction
Liane Mahlmann Kipper 6
Liane Mahlmann Kipper
Objective
7
To capture the emotions of the student, through a
specific software during the process of interaction
with the VLE, and together with the result of the
assessment of student learning in an activity
course, to realize the existence of the relationship
between emotion and cognition, and use this
information to make improvements in learning.
Liane Mahlmann Kipper
Theoretical Foundation
9
According to Nunes (2012), when computational tools may
infer emotions of users in applications such as VLEs, it is
possible to say that these tools promote affective computing.
In Nunes et al. (2011), say that in the process of learning…
• The teacher take on the role of mediator;
• Students seek more knowledge.
Liane Mahlmann Kipper
Theoretical Foundation
10
Infer
Student’s emotion:
Joy, Sadness, Anger,
Fear, Disgust or
Surprise.
Action: Adaptation of VLE
according to the emotion
inferred.
According to Duran et al. (2004), cognition is a knowing process
that involves some aspects such as attention, perception,
memory, judgment, reasoning, imagination, thought and
speech.
For the student to have improvement in the learning process,
he/she must be motivated for cognitive processes to be
achieved in all respects.
Liane Mahlmann Kipper
Method of Inference and the VLE
11
• To infer the emotion of the student in the Virtual Learning
Environment, the method will use software that was
developed at UNISC.
(Böhm, 2011)
Liane Mahlmann Kipper
Method of Inference and the VLE
12
• The VLE was developed by a research group at UNISC.
This environment has already expressed emotions through
intelligent agents.
Methodology
13
Stages of work:
Liane Mahlmann Kipper
Capturing the emotion of the student by the use of software that makes the inference
through facial expressions.
Integrating inference method with VLE.
Defining moments when the emotion of the
student will be inferred.
Assessing learning.
Adapting the presentation of the content.
Liane Mahlmann Kipper 14
Integrating inference method with VLE.
Defining moments when the emotion of the
student will be inferred.
Assessing learning in order to prove the hypothesis in this
paper.
To Capture the emotion of the student by the use of software
that makes the inference through facial expressions.
Methodology
Adapting the presentation of the content.
Capturing the emotion of the student by the use of software that makes the inference
through facial expressions.
Liane Mahlmann Kipper 15
Integrating inference method with VLE.
Defining moments when the emotion of the
student will be inferred.
Assessing learning in order to prove the hypothesis in this
paper.
Integrating inference method with VLE.
Methodology
Adapting the presentation of the content.
.
Capturing the emotion of the student by the use of software that makes the
inference through facial expressions.
Liane Mahlmann Kipper 16
Capturing the emotion of the student by the use of software that makes the
inference through facial expressions.
Integrating inference method with VLE.
Defining moments when the emotion of the
student will be inferred.
Assessing learning in order to prove the hypothesis in this
paper.
Defining moments when the emotion of the student will be
inferred.
Methodology
Adapting the presentation of the content.
Liane Mahlmann Kipper 17
Capturing the emotion of the student by the use of software that makes the
inference through facial expressions.
.
Integrating inference method with VLE.
Defining moments when the emotion of the
student will be inferred.
Assessing learning in order to prove the hypothesis in this
paper.
Adapting the presentation of the content.
Adapting the presentation of the content.
Methodology
Liane Mahlmann Kipper 18
Capturing the emotion of the student by the use of software that makes the
inference through facial expressions.
.
Integrating inference method with VLE.
Defining moments when the emotion of the
student will be inferred.
Assessing learning in order to prove the hypothesis in this
paper.
Adapting the presentation of the content.
Assessing learning.
Methodology
Liane Mahlmann Kipper 19
Conclusion
• This research aims to capture the emotion of the
student through software that analizes facial
expressions;
• To make this software work with VLE, or taking part
in it, which sets up an integration between both;
• To adapt the content of the VLE according to the
inferred emotion;
• And to assess student learning to find out if the
process was useful or not in improving student
learning.
Liane Mahlmann Kipper
References
21
• BOHM, Diogo Luiz. Detecção automática de expressões faciais em imagens de faces humanas.
2011. 67 f. Monografia (Graduação) - Universidade de Santa Cruz do Sul, 2011.
• DURAN, Kelly Marion; VENANCIO Lauro Ramos; RIBEIRO Lucas dos Santos. Influência das
Emoções na Cognição. UNICAMP, 2004.
• KAPOOR, A. e PICARD, R. E. Multimodal Affect Recognition in Learning Environments, In: ACM
MM’05, November 6-11, Singapore. 2004.
• PIAGET, Jean (1983). A epistemologia Genética/Sabedoria e Ilusões da Filosofia/Problemas de
Psicologia Genética. 2. Ed São Paulo: Abril Cultura, 1983. (Os pensadores).
• PICARD, R.W.; Papert, S.; Bender, W.; Blumberg, B.; Breazeal, C.; Cavallo, D.; Machover, T.;
Resnick, M.; Roy, D.; Strohecker, C. Affective Learning-A Manifesto. BT Technical Journal, Volume
22, No. 4, pp. 253-269. October, 2004.
• LONGHI, Magalí Teresinha; BERCHT, Magda; BEHAR Patricia Alejandra (2007). Reconhecimento de
Estados Afetivos do Aluno em Ambientes Virtuais de Aprendizagem. Porto Alegre, UFRGS. V. 5 Nº 2,
Dezembro, 2007.
• NUNES Maria Augusta S. N; REHEN Almerindo; BEZERRA Jonas S.; ROCHA Alex; SANTOS Celso
A. S. Uso do Kinect para a extração de caracterísiticas afetivas do usuário. Anais do XXII SBIE –
XVII WIE. Aracaju, 2011.
• NUNES Maria Augusta Silveira Netto. Computação Afetiva personalização de interfaces, interações e
recomendações de produtos, serviços e pessoas em ambientes computacionais. Capítulo de Livro.
2012, v. 1, p. 115-151.