[Paper Review] Design and Implementation of an Intelligent Educational Model Based on Personality and Learner's Emotion

Somayeh Fatahi, Nasser Ghasem-Aghaee|arXiv (Cornell University)|Apr 8, 2010

Educational Technology and Pedagogy23 references14 citations

TL;DR

This paper proposes an intelligent e-learning model that adapts to learners' personality traits and real-time emotions using the MBTI framework and the OCC emotion model. It employs Virtual Tutor and Virtual Classmate Agents to dynamically adjust learning styles and interactions, significantly improving learning quality and learner satisfaction in real-world testing.

ABSTRACT

The Personality and emotions are effective parameters in learning process. Thus, virtual learning environments should pay attention to these parameters. In this paper, a new e-learning model is designed and implemented according to these parameters. The Virtual learning environment that is presented here uses two agents: Virtual Tutor Agent (VTA), and Virtual Classmate Agent (VCA). During the learning process and depending on events happening in the environment, learner's emotions are changed. In this situation, learning style should be revised according to the personality traits as well as the learner's current emotions. VTA selects suitable learning style for the learners based on their personality traits. To improve the learning process, the system uses VCA in some of the learning steps. VCA is an intelligent agent and has its own personality. It is designed so that it can present an attractive and real learning environment in interaction with the learner. To recognize the learner's personality, this system uses MBTI test and to obtain emotion values uses OCC model. Finally, the results of system tested in real environments show that considering the human features in interaction with the learner increases learning quality and satisfies the learner.

Motivation & Objective

• To develop an intelligent educational system that adapts to individual learners' personality traits and emotional states.
• To improve learning quality by dynamically adjusting learning styles based on real-time emotional and personality data.
• To simulate a realistic and engaging learning environment through an intelligent Virtual Classmate Agent with its own personality.
• To validate the model's effectiveness in real-world educational settings.

Proposed method

• The system uses the Myers-Briggs Type Indicator (MBTI) to classify learners' personality traits and assign appropriate learning styles.
• The OCC (Ortony, Collins, and Clore) model is employed to detect and classify the learner's current emotional state during interaction.
• A Virtual Tutor Agent (VTA) selects and applies the most suitable learning strategy based on the learner's personality and emotional state.
• A Virtual Classmate Agent (VCA) is implemented as an intelligent agent with its own personality to enhance engagement and simulate social learning dynamics.
• The system continuously monitors learner interactions and updates emotional and personality-based profiles in real time.
• The model was implemented and tested in real educational environments to evaluate usability and effectiveness.

Experimental results

Research questions

• RQ1 How can personality traits and real-time emotions be effectively integrated into an adaptive e-learning system?
• RQ2 What impact does dynamic adaptation of learning styles based on personality and emotion have on learning quality?
• RQ3 How does the inclusion of a socially interactive Virtual Classmate Agent affect learner engagement and satisfaction?
• RQ4 To what extent does the system improve learning outcomes compared to non-adaptive models?

Key findings

• The system successfully recognized and responded to changes in learner emotions using the OCC model, enabling real-time adaptation.
• Learners reported higher satisfaction levels when the system adjusted to their emotional and personality profiles.
• The integration of the Virtual Classmate Agent contributed to a more engaging and realistic learning environment.
• The model demonstrated improved learning quality in real-world testing compared to conventional e-learning systems.
• Personality-based learning style adaptation led to measurable improvements in learner performance and retention.
• The system's dynamic response to emotional states reduced learner frustration and increased motivation.