Automatic generation of emotions in tutoring agents for affective e-learning in medical education Efthymios Alepis ⇑ , Maria Virvou Department of Informatics, University of Piraeus, 80 Karaoli & Dimitriou St., 18534 Piraeus, Greece article info Keywords: Medical e-learning Affective agents Emotion generation Intelligent tutoring systems abstract Web-based education is particularly appropriate for remote teaching and learning at any time and place, away from classrooms and does not necessarily require the presence of a human instructor. The need for time and place independence is even greater in some cases, such as for medical instructors who are usu- ally doctors that have to treat patients on top of their tutoring duties. However, this independence from real teachers and classrooms may influence negatively the students who may feel deprived of the benefits of human–human interaction. In this paper we describe a novel approach for incorporating affective char- acteristics into e-learning through an authoring tool. The authoring tool incorporates and adapts princi- ples of a cognitive theory for modeling possible emotional states that a tutoring agent may use for educational purposes. Medical instructors may use this authoring tool to create their own educational characters that will interact affectively with their students in the e-learning environment. Ó 2011 Elsevier Ltd. All rights reserved. 1. Introduction Medical students have many learning and training obligations, ranging from clinical work at hospitals to reading theory and doing coursework. A similar situation is faced by medical instructors who are usually doctors that have to treat patients on top of their tutor- ing duties. In view of these obligations, the technology of mobile computing can assist considerably the medical educational process, since both students and instructors may have access to educational software applications from anywhere at anytime through handheld devices of mobile phones. However, this independence from real teachers and classrooms may affect the educational process in a negative way because as Goleman (1995) points out, how people feel may play an important role on their cognitive processes as well. As it is also stated in Falout, Elwood, and Hood (2009), negative affective states of learners can negatively influence their attitudes and behaviors, degrade classroom group dynamics and teacher’s motivation, and result in long-term and widespread negative learning outcomes. At the same time, teachers could overcome difficulties in students’ man- agement by knowing the affective states of their students (Hwang & Yang, 2009). Our main scope is to address these problems by providing an authoring tool for medicine that constructs animated medical agents with emotional interaction capabilities, thus rendering human–computer interaction for e-learning more human-like. Medical instructors may use this authoring tool to create their own educational characters that will interact with their students in the medical e-learning environment. Agents may be parameter- ized in many aspects, the way they speak, the pitch, speed and vol- ume of their voice, their body-language, their facial expressions and the content of their messages. Additionally, for educational purposes, agents may express spe- cific emotional states and this capability is based on the incorpora- tion of the OCC (Ortony, Clore, & Collins, 1990) cognitive model of emotions, proposed by Ortony et al. (1990). The novel system that we developed encapsulates an affective authoring module that re- lies on the OCC theory for modeling possible emotional states of users–students as well as for proposing tactics to medical instruc- tors in order to improve the interaction between tutoring agents and medical students. Through the incorporation of the OCC mod- el, the system may suggest that a tutoring agent should express a specific emotional state to the medical student for the purpose of motivating her/him while s/he learns. Consequently, the agent may become a more effective teacher, reflecting the instructors’ vision of teaching behavior. In many cases it would be extremely useful to have such facil- ities in handheld devices, such as mobile phones rather than desk- top or portable computers so that additional assets may be gained. Such assets include device independence as well as more indepen- dence with respect to time and place in comparison with web- based education using standard PCs. This is certainly the case for medical education due to the heavily loaded schedule of doctors– instructors and medical students. At the current state, there are not many mature mobile authoring systems, since the technology 0957-4174/$ - see front matter Ó 2011 Elsevier Ltd. All rights reserved. doi:10.1016/j.eswa.2011.02.021 ⇑ Corresponding author. E-mail addresses: talepis@unipi.gr (E. Alepis), mvirvou@unipi.gr (M. Virvou). Expert Systems with Applications 38 (2011) 9840–9847 Contents lists available at ScienceDirect Expert Systems with Applications journal homepage: www.elsevier.com/locate/eswa