Future Trends for Conversational Agents

Abstract

In the last decades, there has been a great evolution in the field of Conversational Agents. Currently, there are agents to assist the navigation in Web pages, support elder users when interacting with some computer application to remind them which medicines they should take during the day, or to enhance the learning process by allowing students to review with systems that adapt themselves to their previous knowledge and rhythm of study. In this chapter, the goal is to provide a summary of the future trends that can be envisaged for the future of the field. It is our insight that the future of Conversational Agents are to become pervasive and natural in our daily lives.

A Review of the Practical Applications of Pedagogic Conversational Agents to Be Used in School and University Classrooms

“…It is advisable to follow a UCD to adapt the design of the PCA to the needs of the students, which could be the key to overcome many limitations found (i.e., interaction modalities, specific domains, limited language interaction, etc.). It is not the same to design an agent for little children than for High School or University students [39,53,59,62].…”

“…Hence, the fifth criterion would be: The sixth criterion is the adaptative-evolution possibilities. It has been included from the inspiration of reading the work of Liebermen [55], in which he claimed that autonomous agents can show adaptive and evolution possibilities, i.e., the agent adapts its behavior to each student, and learns how to evolve to interact better depending on previous interactions [56][57][58][59]. PCAs may not have either adaptive or evolution possibilities as in 6.1, to have adaptive possibilities to modify their dialogue and/or gestures to the student as in 6.2, to have evolution possibilities and to learn from the previous sentences of the dialogue to generate different interactions (verbal and or non-verbal) as in 6.3, and even to have adaptive and evolution possibilities so that from the learning of previous and present interactions the behavior and/or dialogue of the agent changes as in 6.4.…”

“…Agents could learn from previous mistakes in the dialogue, and give the impression that they are actually talking to the student (as in a human-to-human dialogue in which we remember what we said and adapt ourselves to the context and dialogue of the person to whom we are talking). Advances in Natural Language Processing could improve the student-agent dialogue and avoid the frustration feeling that some students can get if the agent makes mistakes because it does not understand what the student is saying, or it is in a language that the agent cannot process [28,59]. Nine out of the 12 reviewed agents have been designed to be used with a PC.…”

Can a Learning Companion Be Used to Continue Teaching Programming to Children Even During the COVID-19 Pandemic?

“…There are many different PCAs applied to different domains and to develop competences from Pre-Primary to Higher Education [39] , [40] . Some domains in which PCAs have been used successfully are: Science [36] , Math [41] , Languages [42] , Storytelling [43] , Social skills [44] , Operating Systems [45] and Programming [46] for Higher Education in object-oriented languages such as C++ [47] and JAVA [48] , [49] , procedural languages such as C [50] , database management such as SQL [51] and the tangible programming Tern in Museums [52] , [53] .…”

“…Learning companions can also be considered as a subtype of PCAs in which the emphasis is on the companion role of the agent, in an individual or collaborative use [62] in contrast to agents in which the main role is a teacher or even a student role [39] . Studies have shown that conversational agents acting as educational companions or tutors can facilitate learning [63] , [64] .…”