Design and implementation of a conversational agent to stimulate teacher-students interactions in synchronous on-line lecture environments

Recently, many universities and schools have switched to online teaching due to the COVID-19 pandemic. Distance learning could limit social interaction between teachers and peer-learners. As this may demotivate learners in the long term, better social engagement providing solutions such as Virtual Reality (VR) can be used for teaching and learning. In the field of technology-enhanced learning, research has indicated that using conversational agents to engage learners in one-to-one (student-agent) tutorial dialogues can improve students' comprehension and foster students' engagement and motivation. Such agents try to simulate the behavior of a human instructor or tutor and engage in a discussion with a learner on a series of predefined topics. Research in the field of Computer-Supported Collaborative Learning has revealed that unsolicited conversational agent interventions can intensify the knowledge exchange among learning partners and increase students' explicit reasoning and participation levels. In this thesis, it was designed a virtual conversational agent (VCA) intended to act as a classmate to stimulate teacher-student interactions in an on-line learning environment during a synchronous lecture. The VCA was experimented in a controlled lecturing scenario. It was implemented to be plugged into Mozilla Hubs, which provides the virtual classroom in which a real teacher teaches to a real student and his/her virtual and active classmate (a Solar System lecture was used). The VCA exploits DialogFlow to interpret the meaning of conversations and interacts appropriately to increase the level of interaction and engagement during the lesson. Experiments were designed to evaluate the potential of conversational agents and co-learning with a virtual classmate (agent) to increase engagement, commitment and enjoyment of learning in VR.