Robotic Chinese language tutor: personalising progress assessment and feedback or taking over your job?

Abstract

Purpose The shortage of Chinese language teachers have been identified as a pressing issue globally. This paper aims to respond to the needs by investigating and designing the learning innovation with autonomous programmable robot, NAO. Design/methodology/approach By thoughtfully embedding NAO robot into teaching basic Chinese language, this research demonstrates an inquiry qualitative case study of artificial intelligence design principles and learning engagement with rule-based reasoning and progress test design. Findings This state-of-the arts robot use its emotion recognition and body language automated (LED eye with various colours) to demonstrate the Chinese words, to increase learners’ understanding and enhance their memory of the words learned. The responses conclude that the novel learning experience is more fun and interesting, thus the engagement from the axis of novelty, interactivity, motivation and interest is enhanced. Research limitations/implications It is recognised that the number of research participants was small, but the qualitative finding demonstrate key issues and recommendation that may inspire future empirical research. Practical implications Today, robotics is a rapidly growing field and has received significant attention in education. Humanoid robots are now increasingly used in fields such as education, hospitality, entertainment and health care. Educational robots are anticipated to serve as teaching assistants. Originality/value The learning engagement paradigm has shifted from manual engagement to personal response systems or mixed-reality on mobile platforms, and now with the humanoid robot, the recommendation of four principles and future work and for designing humanoid robot as a language tutor are discussed. The educational robot model can be changed to a newer robot such as CANBOT U05E.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 46 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.