Communication Design for an Educational AI Chatbot: Analyzing Cipherbot's Communication Style and Challenges DOI Creative Commons
Joni Salminen, Soon-Gyo Jung, Johanne Medina

и другие.

Опубликована: Окт. 8, 2024

We analyzed the communication patterns of Cipherbot, an educational AI chatbot that addresses validation and transparency problems in AI-student interaction, with 44 undergraduate business students using system. Findings show Cipherbot delivers information grounded learning materials, primarily focusing on statements fact, a 99% occurrence rate. Also, about third (31%) Cipherbot's messages to contain example, which adheres pedagogical best practices. However, more than (36%) also contained traces opinion, particularly normative how companies or individuals should behave. demonstrates some level social etiquette, thank yous apologies (7%), but it rarely engages requests for information, clarifications comprehension checks–as these categories might be useful student engagement, future exploration into diversifying style support is required. Student feedback suggests usability issues chatbots comprise both communicational technical issues, e.g., incompleteness redundancy–iterative testing prompts could address many challenges. Based our findings, we make six propositions students' interaction chatbots.

Язык: Английский

Communication Design for an Educational AI Chatbot: Analyzing Cipherbot's Communication Style and Challenges DOI Creative Commons
Joni Salminen, Soon-Gyo Jung, Johanne Medina

и другие.

Опубликована: Окт. 8, 2024

We analyzed the communication patterns of Cipherbot, an educational AI chatbot that addresses validation and transparency problems in AI-student interaction, with 44 undergraduate business students using system. Findings show Cipherbot delivers information grounded learning materials, primarily focusing on statements fact, a 99% occurrence rate. Also, about third (31%) Cipherbot's messages to contain example, which adheres pedagogical best practices. However, more than (36%) also contained traces opinion, particularly normative how companies or individuals should behave. demonstrates some level social etiquette, thank yous apologies (7%), but it rarely engages requests for information, clarifications comprehension checks–as these categories might be useful student engagement, future exploration into diversifying style support is required. Student feedback suggests usability issues chatbots comprise both communicational technical issues, e.g., incompleteness redundancy–iterative testing prompts could address many challenges. Based our findings, we make six propositions students' interaction chatbots.

Язык: Английский

Процитировано

0