Investigating the Usability of an Educational AI Chatbot by Middle School Teachers and Students for Enhanced Learning
Abstract
Kholoud Khalil Aldous , Joni Salminen , Soon-gyo Jung , Jinan Y. Azem , Johanne Medina , Salar M. Khan , Amani Alabed , Bernard J. Jansen The evaluation of AI educational dialogue systems for middle-school students has been limited. This study employs a state-of-the-art AI chatbot that answers students’ questions exclusively based on educator-provided learning materials. Following an initial assessment by 10 middle-school teachers using the Chatbot Suitability Questionnaire, we conducted a mixed-method intervention user study involving 18 middle-school students to explore usability expectations, knowledge acquisition, and learning experience. Findings reveal that interacting with the AI chatbot enhanced self-reported knowledge acquisition, improved learning outcomes measured by test scores, and maintained student interest for future use. The chatbot achieved a usability score of 71.44% (± 16.28), attributed mainly to its high answer accuracy and effective interpretation of student input. Error management emerged as the most critical usability factor.
Team
Tools
Cipherbot: AI-Powered Transformation of Learning
Cipherbot is an AI teaching and learning platform that turns existing course and curriculum materials into AI-generated lesson plans, slides, narrated videos, study guides, and assessments, while giving learners a 24/7 multilingual tutor that answers only from the instructor’s content, with citations back to the source. Built for the full education spectrum—from national ministry deployments to K-12 schools, universities, and corporate training partners—it combines configurable AI pedagogy, early at-risk-student analytics, automated grading, and full LMS integration. Pilot-tested and adopted by institutions across multiple countries—including Qatar, Korea, Australia, Finland, China, Vietnam, and Indonesia—Cipherbot has served over 4,200 active users, including 400+ teachers and 3,000+ students across 800+ classes, all as part of a social-impact initiative bringing safe, citation-backed AI into everyday teaching and learning.





