Stergios Tegos

A Configurable Conversational Agent to Trigger Students’ Productive Dialogue: A Pilot Study in the CALL Domain

Conversational agents constitute a specific type of ITSs that has been reportedly proven successful in helping students in one-to-one settings, while recently their impact has also been explored in computer-supported collaborative learning (CSCL). In this work, we present MentorChat, a dialogue-based system that employs a configurable and domain-independent conversational agent for triggering students’ productive dialogue. After a system overview with an emphasis on design rationale and system architecture, we present a pilot study, where the agent is evaluated in the context of the computer-assisted language learning (CALL) domain. Thirty students collaborated in small groups trying to accomplish three different tasks. MentorChat conversational agent supported each group discussion differently in each task providing (a) ‘weak’-directed interventions and/or (b) undirected interventions. The study results indicate that ‘weak’-directed agent interventions can be more effective than undirected interventions by means of increasing the level of explicit reasoning, and thus productive dialogue. Some encouraging results concerning the system usability and user acceptance are also presented.

Exploiting Web Conferencing to Support Collaborative Learning

This paper examines whether it is possible for web conferencing platforms to support collaborative learning scenarios. Two web conferencing platforms, an open source and a commercial one, are compared and evaluated in two case studies in tertiary education. The final conclusion of this study is that both platforms are capable of supporting collaborative learning activities with great success.

Conversational agents for academically productive talk: a comparison of directed and undirected agent interventions

Conversational agents that draw on the framework of academically productive talk (APT) have been lately shown to be effective in helping learners sustain productive forms of peer dialogue in diverse learning settings. Yet, literature suggests that more research is required on how learners respond to and benefit from such flexible agents in order to fine-tune the design of automated APT intervention modes and, thus, enhance agent pedagogical efficacy. Building on this line of research, this work explores the impact of a configurable APT agent that prompts peers to build on prior knowledge and logically connect their contributions to important domain concepts discussed in class. A total of 96 computer science students engaged in a dialogue-based activity in the context of a Human-Computer Interaction (HCI) university course. During the activity, students worked online in dyads to accomplish a learning task. The study compares three conditions: students who collaborated without any agent interference (control), students who received undirected agent interventions that addressed both peers in the dyad (U treatment), and students who received directed agent interventions addressing a particular learner instead of the dyad (D treatment). The results suggest that although both agent intervention methods can improve students’ learning outcomes and dyad in-task performance, the directed one is more effective than the undirected one in enhancing individual domain knowledge acquisition and explicit reasoning. Furthermore, findings show that the positive effect of the agent on dyad performance is mediated by the frequency of students’ contributions displaying explicit reasoning, while most students perceive agent involvement favorably.

MentorChat: Introducing a Configurable Conversational Agent as a Tool for Adaptive Online Collaboration Support

Research in the field of computer-supported collaborative learning (CSCL) has systematically indicated that providing adaptive support to collaborating students is an efficient way of improving the outcomes of the collaborative learning activity. In this paper we introduce Mentor Chat, a web-based system that supports collaborative learning by utilizing a Conversational Agent. This agent, which can be easily configured through Mentor Chat authoring environment, aims to intelligently facilitate and trigger the discussion that takes place among partners. To achieve this, Mentor Chat models the domain through a series of key concepts and enables the teacher to define the form of agent intervention when a key concept is traced in students¢ dialogue. We present the system architecture and initial field evaluation data from two studies focusing on end-user acceptance of the system. We also discuss future system improvements and research agenda to explore the impact of Mentor Chat in collaborative learning settings.

Using Microworlds to Introduce Programming to Novices

Introduction to programming is a traditional and compulsory course for first year Computer Science students. However, research in the field of computer science education has highlighted that many students lack on problem solving and computational thinking skills. These issues provoke questions in the academic community as to whether the learning methodology of introductory to programming courses is appropriate. As regards the pedagogical procedure in general, the teacher-centered model was amended with the introduction of Interactive Learning Environments, which promote distributed learning. In this paper, we examine the fundamental skills needed for introductory to programming courses. Additionally, we focus on some of the most popular micro worlds and evaluate them in terms of educational suitability.

An Investigation of Conversational Agent Interventions Supporting Historical Reasoning in Primary Education

This work examines the efficiency of an agent intervention mode, aiming to stimulate productive conversational interactions and encourage students to explicate their historical reasoning about important domain concepts. The findings of a pilot study, conducted in the context of primary school class in Modern History, a suggest a favorable student opinion of the conversational agent, b indicate that agent interventions can help students to engage in a transactive form of dialogue, where peers build on each others reasoning, and c reveal a series of interaction patterns emerging from the display of the agent interventions.

Conversational Agents for Learning: How the Agent Role Affects Student Communication

Conversational pedagogical agents guide and scaffold student dialogue using natural language both in individual and collaborative learning settings. Although conversational agents have been developed to meet a wide variety of educational needs, there are still open research questions concerning the effective design of the agents. This chapter presents the results of an experimental collaborative learning activity exploring whether the different agent roles (peer or tutor) may affect the students’ perceptions of the agent or their conversational style in their responses to it. The study findings provide valuable insights into how the different agent appearance and communication styles can have an impact on the degree of formality in students’ utterances.