Teaching a Conversational Agent using Natural Language: Effect on Learning and Engagement

Conversational teachable agents offer a promising platform to support learning, both in the classroom and in remote settings. In this context, the agent takes the role of the novice, while the student takes on the role of teacher, eliciting the Protégé effect, a pedagogical phenomenon known to increase engagement in the teaching task, and also improve cognitive outcomes. In prior work, interactions with teachable agents show frequent use of interface elements to support learning, and few examples utilise natural language as the sole interaction modality between both user and agent. This work investigates the effect of teaching using natural language while interacting with a virtual agent via the Curiosity Notebook on learning outcomes and engagement. A method of teaching by selecting sentences from source material is compared to paraphrasing from the source material and typing. The results indicate that teaching by paraphrasing in natural language is perceived as being more helpful for learning, but that this perception of improvement is not reflected in actual learning gain over a fixed interaction. Participants also show a short-term preference for teaching via sentence-selection, which they perceive as requiring less effort. There is a positive relationship between the amount of paraphrasing users engage in and improved learning outcomes.