EMOTE (project)

From Wikipedia, the free encyclopedia
Jump to: navigation, search

EMOTE [1] is a collaborative project that aims to develop artificial tutors capable of emotionally engaging with learners. The project is funded by a grant from the European Commission under the Seventh Framework Programme.

The acronym EMOTE stands for EMbOdied-perceptive Tutors for Empathy-based learning.

Objectives[edit]

The primary goals of the EMOTE project are to research the role of pedagogical and empathic interventions in the learning process, and to explore how the exchange of socio-emotional cues with an artificial tutor can create a sense of connection with the learner. The effects of different types of artificial tutors (e.g. virtual and robotic) on the above in both formal and informal settings will also be examined. Finally, the EMOTE project will develop a showcase, so as to ground the research in a concrete classroom scenario.[1]

Context[edit]

Significant work has been devoted to the design of artificial tutors with human capabilities, yet these systems still lack the personal, empathic elements that characterise a traditional teacher. This means that artificial tutors often fail to engage and motivate students in the same way a human teacher does. To address this issue, research on intelligent tutoring systems has recently shifted towards a more learner-centric approach to endow artificial tutors with the ability to perceive the emotions experienced by learners and incorporate these into teaching strategies that build more effective computer-based learning systems.[2]

Recent research on artificial companions showed the importance of embodiment, or the physical form in which an artificial intelligence agent is represented: experiments comparing robots with their virtual representations showed that the robotic embodiment was preferred by users in terms of social presence,[3] enjoyment [4] and performance.[5] This may have been related to the robots' size, realism, shared physical space, physical presence and perceived social presence.[6]

This opens up opportunities for novel contributions in the field of artificial tutors. Socially intelligent robots are increasingly being studied as partners that collaborate and do things with people,[7] making the use of robotic platforms as tools for experimental learning more approachable.[8]

Project description[edit]

The EMOTE project started on 1 December 2012 and is scheduled to last for 36 months (3 years). Project tasks include:

  1. Defining and creating a new generation of embodied empathic artificial tutors (EEATs) to support personalised learning
  2. Developing models of socio‐emotional bonding between learners and embodied empathic artificial tutors
  3. Designing and developing a computational framework for affect recognition to support affect modelling in EEATs
  4. Studying the impact of different embodiments on learning and learner engagement
  5. Exploring the possibility of migrating empathic tutors across platforms and embodiments (i.e. comparing the benefits of virtual versus robotic tutors)
  6. Developing a set of learner‐centred scenarios where different teaching strategies are adapted to the learners' emotional states
  7. Designing and developing an empathic dialogue modelling system, empirically driven, to be used in EEATs
  8. Exploring the use of an EEAT to teach geography to schoolchildren
  9. Designing and developing an evaluation methodology to assess the tutor’s effectiveness in the classroom
  10. Assessing the impact that the EEAT has on the learning and engagement of children in the concrete scenarios created
  11. Defining a framework and a set of guidelines for the construction of EEATs
  12. Disseminating the EMOTE results to appropriate audiences and investigating exploitation opportunities

Consortium[edit]

In order to achieve these objectives, the EMOTE consortium brings together experts who carry out interdisciplinary research on affect recognition, learner models, adaptive behaviour and embodiment for human-robot interaction in learning environments, grounded in psychological theories of emotion in social interaction and pedagogical models for learning facilitation.

The EMOTE team includes individuals from:

See also[edit]

References[edit]

  1. ^ Lightfoot, Liz (17 February 2013). "Touchy-feely robot to teach in school". The Sunday Times. Retrieved 19 July 2013. 
  2. ^ W. Burleson, "Affective Learning Companions: Strategies for Empathetic Agents with Real-Time Multimodal Affective Sensing to Foster Meta-Cognitive and Meta-Affective Approaches to Learning, Motivation, and Perseverance," PhD Thesis, Massachusetts Institute of Technology 2006..
  3. ^ C. Kidd, "Sociable Robots: The Role of Presence and Task in Human-Robot Interaction," 2003.
  4. ^ A. Pereira, C. Martinho, I. Leite, and A. Paiva, "iCat the chess player: the influence of embodiment in the enjoyment of a game," in Proceedings of the 7th International Joint Conference on AAMAS , Estoril, Portugal, 2008, pp. 1253-1256
  5. ^ C. Bartneck, "eMuu - an embodied emotional character for the ambient intelligent home," 2002
  6. ^ L. Hoffmann and N.C. Krämer, "How Should an Artificial Entity be Embodied? Comparing the Effects of a Physically Present Robot and its Virtual Representation," in Proceedings of Workshop on Social Robotic Telepresence, HRI 2011, Lausanne, Switzerland, 2011
  7. ^ C. Breazeal, "Role of expressive behaviour for robots that learn from people," Philosophical Transactions of the Royal Society B, vol. 364, pp. 3527–3538, 2009
  8. ^ L. Leite, G. Castellano, A., Martinho, C. Pereira, and A. Paiva, "Modelling Empathic Behaviour in a Robotic Game Companion for Children: an Ethnographic Study in Real- World Settings," in To appear in the Proceedings of the ACM/IEEE International Conference on Human-Robot Interaction, 2012

External links[edit]