Using Conceptual Models to Implement Natural Language Pedagogic Agent-Student Conversations

Using Conceptual Models to Implement Natural Language Pedagogic Agent-Student Conversations

Diana Pérez-Marín (Universidad Rey Juan Carlos, Madrid, Spain) and Carlos Caballero (Universidad Rey Juan Carlos, Madrid, Spain)
DOI: 10.4018/ijicst.2013070103
OnDemand PDF Download:
No Current Special Offers


The last several decades have seen a growing trend in incorporating pedagogic conversational agents in interactive learning environments. Software systems have increasingly integrated intelligent virtual agents that can interact with students in natural language to fulfill specific tasks such as reviewing content or providing tutor training. The use of an agent-based approach in education has shown many benefits. However, certain design and development issues are still unresolved. This article focuses on the potentials of employing conceptual models to generate agent-student dialog and introduces a new mixed-initiative general domain agent called JARO. The authors report on the procedure for creating the initial conceptual model and discuss its use in guiding agent-student conversations adapted to students' individual learning needs. The stages of implementation of the model as well as the model's viability tested in a proof-of-concept experiment are addressed.
Article Preview

Software systems increasingly integrate pedagogic conversational agents that can interact with students in a natural language to fulfil specific tasks such as reviewing content or providing tutorial training. Pedagogic agents can cohabit the learning environment creating a rich, personalized face-to-face interface for interaction with students (Johnson, Rickel, & Lester, 2000). In this section an overview of ten PCAs, is provided. The agents were selected based on the design features or functionality that they introduce.

Herman the Bug

Lester et al. (1997) created one of the first pedagogic agents for children: Herman the Bug. There were five modes where the agent could be used with different combinations of gestures and verbal directions. The specific application domain in which Herman was tested was biology. Figure 1 demonstrates a snapshot of one of the modes of the agent.

Figure 1.

Pedagogic agent Herman the Bug


A total of 100 students used Herman to design a plant (20 students per each of the five modes) and it was observed that just the presence of the agent had a positive impact on the students––even the ones using the muted agent. However, no real conversation in a natural language occurred in any of the modes, and the interaction was limited to sound clips previously recorded to give the students advice on how to complete the task of designing the plant.

Complete Article List

Search this Journal:
Open Access Articles: Forthcoming
Volume 11: 2 Issues (2021): Forthcoming, Available for Pre-Order
Volume 10: 2 Issues (2020): 1 Released, 1 Forthcoming
Volume 9: 2 Issues (2019)
Volume 8: 2 Issues (2018)
Volume 7: 2 Issues (2017)
Volume 6: 1 Issue (2016)
Volume 5: 1 Issue (2015)
Volume 4: 2 Issues (2014)
Volume 3: 2 Issues (2013)
Volume 2: 2 Issues (2012)
Volume 1: 2 Issues (2011)
View Complete Journal Contents Listing