A Procedure to Create a Pedagogic Conversational Agent in Secondary Physics and Chemistry Education

A Procedure to Create a Pedagogic Conversational Agent in Secondary Physics and Chemistry Education

Diana Pérez-Marín (Universidad Rey Juan Carlos, Móstoles, Madrid, Spain) and Antonio Boza (Universidad Rey Juan Carlos, Móstoles, Madrid, Spain)
DOI: 10.4018/ijicte.2013100107


Pedagogic Conversational Agents are computer applications that can interact with students in natural language. They have been used with satisfactory results on the instruction of several domains. The authors believe that they could also be useful for the instruction of Secondary Physics and Chemistry Education. Therefore, in this paper, the authors present a procedure to create an agent for that domain. First, teachers have to introduce the exercises with their correct answers. Secondly, students will be presented the exercises, and if the students know the answer, and if it is correct, more difficult exercises will be presented. Otherwise, step-by-step natural language support will be provided to guide the student towards the solution. It is the authors’ hypothesis that this innovative teaching method will be satisfactory and useful for teachers and students, and that by following the procedure more computer programmers can be encouraged to develop agents for other domains to be used by teachers and students at class.
Article Preview

Pedagogic Conversational Agents

In this section, an overview of the field of Pedagogic Conversational Agents (PCAs) is presented to introduce the basic necessary context for anyone who wants to create new agents. It is out of the scope of this paper to accomplish a complete review of the state-of-the-art of the field.


The appearance of the agent is a key issue in the design of a PCA. There are studies indicating that a human form for the agent provides advantages to the student-system interaction (Lester et al., 1997; Cassell & Tartaro, 2007). Figure 1 shows a sample of agent with human appearance.

Figure 1.

Sample agent with human appearance (Source: http://www.icogno.com/joan.html)

However, it should be noted that it may not be true for all cases. In particular, some researchers have warned that creating agents that look like perfect humans creates the expectation that it is possible to keep a perfect dialogue with the agent (Norman, 1994; King & Ohya, 1996; Koda & Maes, 1996).

In general, the choice of the appearance of the agent should be dependent on the nature of the task (Mencia, 2011) and the personal features and skills of the users (Xiao, 2006). Figure 2 shows some samples of agents represented by animals, when their goal is just to provide support to the students, so that they do not feel alone when working with the computer (Chen, Liao, Chien & Chan, 2009), and Figure 3 shows agents represented by little children as animated characters who seek the help of the students because they do not know how to complete the homework (Biswas et al., 2009).

Figure 2.

Sample agent with animal appearance (Source: Chen et al., 2009)

Figure 3.

Sample agents represented by animated characters (Source: Biswas et al., 2009)

Complete Article List

Search this Journal:
Open Access Articles: Forthcoming
Volume 15: 4 Issues (2019): 1 Released, 3 Forthcoming
Volume 14: 4 Issues (2018)
Volume 13: 4 Issues (2017)
Volume 12: 4 Issues (2016)
Volume 11: 4 Issues (2015)
Volume 10: 4 Issues (2014)
Volume 9: 4 Issues (2013)
Volume 8: 4 Issues (2012)
Volume 7: 4 Issues (2011)
Volume 6: 4 Issues (2010)
Volume 5: 4 Issues (2009)
Volume 4: 4 Issues (2008)
Volume 3: 4 Issues (2007)
Volume 2: 4 Issues (2006)
Volume 1: 4 Issues (2005)
View Complete Journal Contents Listing