QWriter: Technology-Enhanced Alphabet Acquisition based on Reinforcement Learning

Abstract

In Kazakhstan, the ongoing Cyrillic-to-Latin alphabet shift raises challenges for early literacy development and acquisition in the Kazakh language. This paper proposes the QWriter system to help young children learn the Latin-based Kazakh alphabet and its handwriting. The system consists of a humanoid robot NAO, a tablet with a stylus, and a Reinforcement Learning (RL) agent that learns a child's mistakes and progress to maximize alphabet learning in the shortest period of time by adapting the order of practice words according to the child's mistakes. To evaluate the effectiveness of the QWriter system, we conducted a between-subject design experiment with 59 Kazakh children aged 6-8 years old and compared their learning performance with a human tutor and the CoWriting Kazakh robot system. The results did not support our assumption, we found that the proposed system received significantly higher likability scores than the baseline human tutor.