Let's teach Kibot: Discovering discussion patterns between student groups and two conversational agent designs

Conversational agents can deepen reasoning and encourage students to build on others' knowledge in collaborative learning. Embedding agents in group work, however, presents challenges where groups may ignore the agents, and this calls for designs where students perceive agents as learning partners. This study examines group interactions with two text-based agents (ie, chatbots) that posed as an expert and a less knowledgeable peer in a high school marine biology lesson. Student messages (N = 1764) from 18 groups (52 students ages 14-15) received codes for reasoning, building on prior ideas, and responsiveness to the agents. Results indicate no differences between agents in how often each discussion move occurred. Interestingly, sequential pattern mining suggests that the less-knowledgeable-peer agent prompted groups to show questioning and building on others' ideas, similar to how students may act as peer tutors to the agent. Meanwhile, sequences with the expert agent resembled student-teacher exchange, where groups responded to the agent's nudges and then provided reasoning. Findings illustrate the affordances of embedding humanized features in technology designs to promote discussion.

Automated summary

This study explores the interactions of two text-based agents playing the roles of an expert and a less knowledgeable peer in a high school marine biology lesson. The results show that there were no differences in the frequency of discussion moves between the two agents. Interestingly, the less knowledgeable peer agent prompted groups to question and build on others' ideas, while the expert agent led to student-teacher exchanges where groups responded to the agent's nudges and provided reasoning.