Probabilistic assessment of user's emotions in educational games
read more
Citations
Better to be frustrated than bored: The incidence, persistence, and impact of learners' cognitive-affective states during interactions with three different computer-based learning environments
Building Intelligent Interactive Tutors: Student-centered Strategies for Revolutionizing E-learning
Affective Learning — A Manifesto
Experience-Driven Procedural Content Generation
Affective e-Learning: Using "Emotional" Data to Improve Learning in Pervasive Learning Environment
References
Artificial Intelligence: A Modern Approach
Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference
Affective Computing
The Cognitive Structure of Emotions
Frequently Asked Questions (18)
Q2. What are the contributions in this paper?
The authors present a probabilistic model to monitor a user ’ s emotions and engagement during the interaction with educational games. The probabilistic model the authors present is to be used by decision theoretic pedagogical agents to generate interventions aimed at achieving the best tradeoff between a user ’ s learning and engagement during the interaction with educational games.
Q3. Why is the problem of recognizing emotions so difficult?
The challenge is due to the high level of ambiguity that exists in the mapping between emotional states and the factors that can be used to detect them.
Q4. What is the advantage of a formal probabilistic approach?
The advantage of a formal probabilistic approach is that the model designer only needs to quantify local dependencies among variables.
Q5. What is the purpose of the authors’ discussion of the probabilistic model?
By taking into account different kinds of possibly ambiguous evidence on the user’s emotional state, their probabilistic model aims at reducing the uncertainty that pervades the assessment of user’s affect in situations in which a variety of emotions can arise in relation to a variety of user’s features.
Q6. What is the main difficulty in using probabilistic frameworks?
One of the major difficulties in using probabilistic frameworks based on Bayesian networks is defining the required prior and conditional probabilities.
Q7. What is the utility function of a tutoring-oriented agent?
for instance, the utility function of a tutoring-oriented agent will assign higher values to states characterized by high levels of student learning, giving less importance to the student’s emotional engagement.
Q8. How does the DDN represent the relationships between the student’s goals and game states?
By explicitly representing the probabilistic relationships between emotional states, bodily expressions and techniques available to detect them, their DDN can combine and leverage any available sensor information, and gracefully degrade when such information becomes less reliable.
Q9. What is the probability of an emotion node being involved in the appraisal process?
When an emotion node is not directly involved in the appraisal process at a given time slice, its probability depends only upon the probability of the corresponding emotion node in thewhen additional goals and personality traits are considered, the mapping can be many-tomany.
Q10. What is the main advantage of educational games versus more traditional computer-based tutors?
The main advantage of educational games versus more traditional computer-based tutors is that the former tend to generate a much higher level of students’ positive emotional engagement, thus making the learning experience more motivating and appealing.
Q11. What is the advantage of a model of affect?
The model of affect allows the agent to explicitly interrogate the user only when the available evidence is insufficient to generate a reliable assessment.
Q12. What is the probability of the agent’s action being influenced by the next decision cycle?
At the next decision cycle, this probability may influence the model so that the agent’s action with the highest expected utility is one designed to bring the level of engagement back up.
Q13. How do the authors formalize the behavior of pedagogical agents?
The authors formalize this behavior by designing their pedagogical agents as decision theoretic agents (Howard and Matheson, 1977; Russell and Norvig, 1995) that select actions so as to maximize the outcome in terms of a student’s learning and emotional engagement, as the authors describe in the next section.
Q14. What are the emotions that affect the appraisal of the consequences of an event?
These emotions include: joy and distress toward the event that is appraised by the user; reproach and admiration toward the entity that caused the event; pride and shame toward the entity that caused the event when the entity is oneself .
Q15. How have existing approaches addressed the challenge of recognizing user’s affect?
Existing approaches have tackled the challenge of recognizing user’s affect by trying to reduce the ambiguity in the modeling task.
Q16. How is the appraisal mechanism modeled in the network?
The appraisal mechanism is explicitly modeled in the network by conditioning the nodes representing emotional states to both nodes representing user’s goals and nodes representing interaction events (the node Agent Actions in this case).
Q17. What does the link between the Learning and Emotional State nodes mean?
The links from the Learning and Emotional State nodes to the utility node in Figure 1 indicate that an agent’s utility function is defined over the student’s learning and emotional states.
Q18. Why does the DDN increase the probability of having the goal Succeed_by_my?
This is because evidence of this personality type would increase the probability of having the goal Succeed_by_Myself, which is impaired by the agent’s provision of help and therefore causes the user’s reproach.