Design principles and architecture of a second language learning chatbot
Open accessThe DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Abstract
The purpose of this article is to set out the design principles and architecture of a second language (L2) learning voice chatbot. Building on L2 acquisition theories and chatbot research, in this article, we report on a South Korean government-funded longitudinal project in which we designed and developed a chatbot called “Ellie”. Chatbot Ellie has three chat modes, “General Chat,” “Task Chat,” and “Skills”. In the General Chat mode, L2 users can have short talks about personal information, whereas in the Task Chat mode, they can engage in a wide range of problem-solving L2 tasks to achieve task goals by exchanging meanings with Ellie. The Skills mode offers form-focused language practice. Ellie was piloted among 137 Korean high school students, who used Ellie individually or in a group, for seven weeks in their English classes. The quality of the chatbot was investigated in terms of the appropriateness of language level, continuity of conversation, and success in task performance. Based on the results of the pilot, Ellie appears to have considerable potential to become an effective language learning companion for L2 learners, and has implications for the design and developments of future L2 chatbots.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372 · cited 3×
“…general AI in Kojouharov’s taxonomy) have not yet been successfully developed, although the recent AI developments of big language models such as GPT-3 (Brown et al., 2020) and Switch-C (Fedus et al., 2021) may advance the realization of general AI, with its promise of open domain functionality.”
BackgroundAdvances in natural language processing
Hirschberg, J., & Manning, C. D. (2015) · Science · doi:10.1126/science.aaa8685 · Cited by 1,712
How Large a Vocabulary is Needed For Reading and Listening?
Nation, I. (2006) · The Canadian Modern Language Review · doi:10.3138/cmlr.63.1.59 · Cited by 1,436
The Design and Implementation of XiaoIce, an Empathetic Social Chatbot
Zhou, L., Gao, J., Li, D., & Shum, H.-Y. (2018) · arXiv · doi:10.48550/arxiv.1812.08989 · Cited by 777
Survey on Chatbot Design Techniques in Speech Conversation Systems
A., S., & John, D. (2015) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2015.060712 · Cited by 479 · cited 1×
“According to a survey conducted by Abdul-Kader and Woods (2015), Loebner prize winners such as A.L.I.C.E versions (years 2000, 2001, 2004) and Mitsuku (years 2013, 2016, 2017, 2018, 2019) were built based on advanced pattern matching in AIML.”
MethodChatbot learning partners: connecting learning experiences, interest and competence
Fryer, L. K., Nakao, K., & Thompson, A. (2019) · Computers in Human Behavior · doi:10.1016/j.chb.2018.12.023 · Cited by 470
Lee, J. H., Yang, H., Shin, D., & Kim, H. (2020) · ELT Journal · doi:10.1093/elt/ccaa035 · Cited by 51
Self-citation
Cited by
Koç, F. Ş., & Savaş, P. (2025) · ReCALL · doi:10.1017/s0958344024000168 · Cited by 69
Chen, A., Zhang, Y., Jia, J., Liang, M., Cha, Y., & Lim, C. P. (2025) · Journal of Computer Assisted Learning · doi:10.1111/jcal.13064 · Cited by 67
Lee, S., Jeon, J., & Choe, H. (2025) · TESOL Quarterly · doi:10.1002/tesq.3300 · Cited by 59
Du, J. (., & Kohnke, L. (2026) · Teaching Education · doi:10.1080/10476210.2025.2590694 · Cited by 4
“However, despite AI’s potential, higher education teachers lack guidance on mean-ingfully integrating AI tools into their teaching practices (Kim et al., 2022; Yang et al., 2022).”
Metadata
- Authors
- Kim, H., Yang, H., Shin, D., & Lee, J. H.
- Venue
- Language Learning & Technology
- Published
- 2022-02-21
- Volume
- 26
- Issue
- 1
- Pages
- 1-18
- ISSN
- 1094-3501 (ISSN-L)
- OpenAlex
- W4413183455
- Cited by
- 51
- References
- 8
- FWCI
- 3.31
- Type
- journal article
- Language
- en
- Open access
- diamond
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.