QWriter: Technology-Enhanced Alphabet Acquisition based on Reinforcement Learning Aidar Shakerimov Department of Robotics and Mechatronics School of Engineering and Digital Sciences Nazarbayev University Astana, Kazakhstan Shamil Sarmonov Department of Robotics and Mechatronics School of Engineering and Digital Sciences Nazarbayev University Astana, Kazakhstan Aida Amirova Graduate School of Education Nazarbayev University Astana, Kazakhstan Nurziya Oralbayeva Graduate School of Education Nazarbayev University Astana, Kazakhstan Aida Zhanatkyzy Department of Robotics and Mechatronics School of Engineering and Digital Sciences Nazarbayev University Astana, Kazakhstan Zhansaule Telisheva Department of Robotics and Mechatronics School of Engineering and Digital Sciences Nazarbayev University Astana, Kazakhstan Arna Aimysheva Department of Robotics and Mechatronics School of Engineering and Digital Sciences Nazarbayev University Astana, Kazakhstan Anara Sandygulova* Department of Robotics and Mechatronics School of Engineering and Digital Sciences Nazarbayev University Astana, Kazakhstan 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 hand- writing. 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 efectiveness of the QWriter system, we conducted a between-subject design exper- iment 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 signifcantly higher likability scores than the baseline human tutor. Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for proft or commercial advantage and that copies bear this notice and the full citation on the frst page. Copyrights for third-party components of this work must be honored. For all other uses, contact the owner/author(s). CHI EA ’23, April 23ś28, 2023, Hamburg, Germany © 2023 Copyright held by the owner/author(s). ACM ISBN 978-1-4503-9422-2/23/04. https://doi.org/10.1145/3544549.3585611 CCS CONCEPTS · Human-centered computing → Empirical studies in HCI; Field studies;· Computer systems organization → Robotics; · Applied computing; KEYWORDS chilld-robot interaction, robot-assisted language learning, Kazakh, reinforcement learning ACM Reference Format: Aidar Shakerimov, Shamil Sarmonov, Aida Amirova, Nurziya Oralbayeva, Aida Zhanatkyzy, Zhansaule Telisheva, Arna Aimysheva, and Anara Sandygulova*. 2023. QWriter: Technology-Enhanced Alphabet Acquisition based on Re- inforcement Learning. In Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems (CHI EA ’23), April 23ś28, 2023, Hamburg, Germany. ACM, New York, NY, USA, 7 pages. https://doi.org/10. 1145/3544549.3585611 1 INTRODUCTION Central to this work is Reinforcement Learning (RL) which has gained traction in human-computer interaction (HCI) [den Hengst et al. 2020]. It is a framework for decision-making processes in which an agent is capable of choosing actions based on the interac- tion with its environment to learn an optimal behavior [Akalin and Loutf 2021; Sutton and Barto 2018]. Evidence from HCI research has shown that RL can be efectively applied in computer-assisted language learning (CALL) [Su et al. 2013], mobile and web-based lan- guage learning applications [Heil et al. 2016], educational robotic