Supervisor: pantelis papadopoulos
topic
Typically, a conversational agent is an automated system or a computer program that usually aims to imitate human conversations through voice commands, text chats or both. Most of the times, such a virtual entity is created to participate in a virtual conversation with humans, which usually takes place in an online environment. A conversational agent usually operates within a well-defined set of rules and parameters that shape its behavior. Such an agent can be designed to provide many functions in real-world settings and can be used in websites or messaging platforms and mobile applications.
In essence, a conversational interface may provide software creators with a new convenient channel for interacting and communicating with their users in a more personalized and engaging manner. The primary reason why conversational agents and voice assistants have drawn so much attention recently is that the technology involved in Natural Language Processing (NLP) has improved substantially and became a lot easier and cheaper to access. Indeed, the rapid increase in interest in conversational agents in the last years is illustrated by the fact that conversational agents appear in many mainstream applications. This opens up interesting new implementations of bots in various scenarios when integrated with various enterprise applications. Indeed, the increased level of engagement in conversational agent platforms holds tremendous potential for enterprises and organizations in a lot of sectors, such as Healthcare, Finance, and Education.
Conversational agents can be used in one-on-one or collaborative settings. In one-on-one settings, a student is interacting with an agent. Studies have shown that tutorial dialogue initiated and controlled by a conversational agent can provide several benefits over a monologue, such as the detection and remediation of failed communication, the correction of inaccurate student knowledge and increased interactivity. In collaborative settings, the agent is monitoring the conversation between two or more students and intervenes to improve the dialogue. In general, these interventions aim at increasing engagement, transactivity, or productive dialogue.
The overarching research question of this topic is to identify and analyze the agent characteristics and interventions that could enhance the learning experience for the individual and/or the group. Alternatively, the focus may be on the teacher and on how conversational agents can be used to support the teacher’s activity in classroom and online settings.
METHOD
Depending on the research question and the targeted audience (individual students, groups, teachers), the study may be based on a comparative analysis of different study conditions or the impact of appropriate intervention within the same condition.
references
Tegos, S., Demetriadis, S., Papadopoulos, P. M., & Weinberger, A. (2016). Conversational agents for academically productive talk: A comparison of directed and undirected agent interventions. International Journal of Computer-Supported Collaborative Learning, 11(4), 417-440.
Tegos, S., & Demetriadis, S. N. (2017). Conversational Agents Improve Peer Learning through Building on Prior Knowledge. Educational Technology & Society, 20(1), 99-111.
colMOOC Project: D2.1 Conversational Agent Model Design. https://colmooc.eu/wp-content/uploads/2021/01/D2.1_colMOOC_CA_ModelDesign-3.pdf