View - ResearchGate

214 Socially Intelligent Agentsin nature, and empirical studies on exploratory learning environments [16] haveshown that they tend to be effective only for those students that already possessthe meta-cognitive skills necessary to learn from autonomous exploration (suchas self-monitoring, self-questioning and self-explanation).In this chapter, we discuss how to improve the effectiveness of educationalgames by relying on socially intelligent agents (SIAs). These agents are activegame characters that can generate tailored interventions to stimulate students’learning and engagement, by taking into account the student’s cognitive states(e.g., as knowledge, goals and preferences), as well as the student’s metacognitiveskills (e.g., learning capabilities) and emotional reactions.2. SIAs as Mediators in Educational GamesWe argue that the effectiveness of educational games can be increased byproviding them with the capability to (i) explicitly monitor how students interactwith and learn from the games; (ii) generate calibrated interventions to triggerconstructive reasoning and reflection when needed.However, this must be done without interfering with the factors that makegames fun and enjoyable, such as a feeling of control, curiosity, triggering ofboth intrinsic and extrinsic fantasies, and challenge [12]. Thus, it is not sufficientto provide educational games with the knowledge that makes more traditionalIntelligent Tutoring Systems effective for learning: an explicit representationof the target cognitive skills, of pedagogical knowledge and of the student’scognitive state. It is fundamental that the educational interventions be deliveredwithin the spirit of the game, by characters that (i) are an integral part of the gameplot; (ii) are capable of detecting students’ lack of engagement, in addition tolack of learning; (iii) know how to effectively intervene to correct these negativeemotional and cognitive states.Basically, these characters must play, in the context of the game, the mediatingrole that teachers and external instructional activities have played duringthe most successful evaluations of the EGEMS prototypes. The requirementthat these agents be socially intelligent is further enforced by the fact thatwe are currently interested in investigating the educational potential of multiplayercomputer games to support collaborative learning. In the last few yearsthere has been increasing research on animated pedagogical agents and there isalready empirical evidence of their effectiveness in fostering learning and motivation[17]. Our work extends existing research toward making pedagogicalagents more socially apt, by enabling them to take into account users’ affectivebehaviour when adapting their interventions and to engage in effective collaborativeinteractions.