TecnoLógicas (Jan 2020)
Designing Pedagogic Conversational Agents through Data Analysis
Abstract
Pedagogical Conversational Agents are systems or programs that represent a resource and a means of learning for students, making the teaching and learning process more enjoyable. The aim is to improve the teaching-learning process. Currently, there are many agents being implemented in multiple knowledge domains. In our previous work, a methodology for designing agents was published, the result of which was Agent Dr. Roland, the first conversational agent for Early Childhood Education. In this paper, we propose the use of Data Analytics techniques to improve the design of the agent. Two new techniques are applied: KDDIAE, application of (Knowledge Discovery in Databases) to the Data of the Interaction between Agents and Students – Estudiantes in Spanish, and BIDAE (use of Data Analytics to obtain information of agents and students). The use of KDDIAE and BIDAE proves the existence of a fruitful relationship between learning analytics and learning design. Some samples of rules related to learning analytics and design are the following: (Learning Analytics) Children who initially do not know how to solve the exercise, after receiving help, are able to understand and solve it à (Learning Design) An agent for small children should be able to provide help. In addition, help should be entertaining and tailored to their characteristics because it is a resource that children actually use; or (Learning Analytics) Younger children use more voice interaction à (Learning Design) An agent interface for young children must incorporate voice commands. A complete list of rules related to learning analytics and design is provided for any researcher interested in PCA design. 72 children were able to use the new Dr. Roland after applying the learning analytics-design rules. They reported a 100 % satisfaction as they all enjoyed interacting with the agent.
Keywords
