2nd International ICST Conference on Mobile Multimedia Communications

Research Article

A multi-agent based system for affective peer-e-learning

  • @INPROCEEDINGS{10.1145/1374296.1374340,
        author={Mohamed Ben Ammar and Mahmoud Neji },
        title={A multi-agent based system for affective peer-e-learning},
        proceedings={2nd International ICST Conference on Mobile Multimedia Communications},
        publisher={ACM},
        proceedings_a={MOBIMEDIA},
        year={2006},
        month={9},
        keywords={E-Learning environment facial interaction multi-agents architecture peer to peer E-learning.},
        doi={10.1145/1374296.1374340}
    }
    
  • Mohamed Ben Ammar
    Mahmoud Neji
    Year: 2006
    A multi-agent based system for affective peer-e-learning
    MOBIMEDIA
    ACM
    DOI: 10.1145/1374296.1374340
Mohamed Ben Ammar1,*, Mahmoud Neji 2,*
  • 1: Institut Supérieur d'Informatique et de Gestion, Kairouan-Tunisia
  • 2: University of Sfax, - Tunisia
*Contact email: Mohamed.Benammar@fsegs.rnu.tn, Mahmoud.Neji@fsegs.rnu.tn

Abstract

Recent research results indicate that cognitive processes are related to emotions. Since emotions are omnipresent in any kind of interaction it can be advantageous to take them into account, particularly in the context of e-learning. Emotions are now seen as closely related to cognition processes including decision-making, memory, attention, etc. Thus, e-learning environments have begun to take into consideration the emotional state of the learner in order to enhance his performance. This paper presents a tool for man-machine interaction which uses facial input. We believe that facial interaction will have its place among the interaction techniques in the near future. Our work concerns the improvement of computer based learning by mean of a lifelike presence in learning environment. Our approach combines Intelligent Tutoring System with research on human emotion in Cognitive Science, Psychology and Communication. According for relations between emotion, cognition and action in contextual learning, we propose an emotional intelligent tutoring system based on multi-agent architecture to design of adaptive distributed collaborative and peer to peer e-learning environments. An emotionally intelligent tutoring system should be able to provide feedback to students, taking into account relevant aspects of the mental state of the student.