Feasibility and Constraints in Applying an AI Chatbot to English Education
0
조회
0
다운로드
62
인용
0
참고문헌
키워드
초록
The present study aimed at investigating the feasibility and constraints in applying an AI chatbot to Englisheducation. For this purpose, seven tasks were presented to the upper (n=27) and lower (n=26) groups (collegestudents vs. high school students) using Mitsuku, a representative chatbot, as a way to utilize the chatbot inEnglish education. The participants chatted with Mitsuku to accomplish these tasks. By analyzing the data from thetask performance, this study showed that Mitsuku's utterances were two times more than the students' utterances,and the difference was larger at the lower group. It also turned out that the text easability of Mitsuku's utterancescorresponded to the grades K2 and K3, and 90% or more of the words making up Mitsuku's utterances wereincluded within the first 3,000 word level. In the case of the lower group, it was confirmed that the shorter thesentence length was, the larger the amount of utterance, and the higher the similarity of conceptual meaningbetween adjacent paragraphs, the more similar to human utterance. In the case of the upper group, the participantsseemed to believe that the higher the diversity of the use of the verbal forms, the more the contribution to theeffectiveness of English education. In addition, the upper group showed that the lower readability level was, thelarger the amount of utterance. As a result, the findings from this analysis could contribute to the educational useof chatbot and the development of a new chatbot as a reference.
Abstract
The present study aimed at investigating the feasibility and constraints in applying an AI chatbot to Englisheducation. For this purpose, seven tasks were presented to the upper (n=27) and lower (n=26) groups (collegestudents vs. high school students) using Mitsuku, a representative chatbot, as a way to utilize the chatbot inEnglish education. The participants chatted with Mitsuku to accomplish these tasks. By analyzing the data from thetask performance, this study showed that Mitsuku's utterances were two times more than the students' utterances,and the difference was larger at the lower group. It also turned out that the text easability of Mitsuku's utterancescorresponded to the grades K2 and K3, and 90% or more of the words making up Mitsuku's utterances wereincluded within the first 3,000 word level. In the case of the lower group, it was confirmed that the shorter thesentence length was, the larger the amount of utterance, and the higher the similarity of conceptual meaningbetween adjacent paragraphs, the more similar to human utterance. In the case of the upper group, the participantsseemed to believe that the higher the diversity of the use of the verbal forms, the more the contribution to theeffectiveness of English education. In addition, the upper group showed that the lower readability level was, thelarger the amount of utterance. As a result, the findings from this analysis could contribute to the educational useof chatbot and the development of a new chatbot as a reference.
참고문헌 (18)
- Abu-Shawar, B, "Integrating CALL systems with chatbots as conversational partners", Computación y Sistemas, 21(4), pp.615~626 (2017)
- Baayen, R. H, "The CELEX lexical database(CD-ROM)" (1995), Linguistic Data Consortium, University of Pennsylvania
- Colby, K, "Artificial paranoia : A computer simulation of paranoid processes" (1975), Elsevier
- Fryer, L, "Bots as language learning tools", Language Learning and Technology, 10(3), pp.8~14 (2006)
- "Coh-Metrix: Analysis of text on cohesion and language" (2004)[URL]
- "RANGE and FREQUENCY programs" (2002)[URL]
- Jones, E. E, "Foundations of social psychology" (1967), John Wiley & Sons
- Kim, J. S, "The effects of human− AI assistant interactions on children’s collaborative language acquisition", master, pp.2017
- "Microsoft’s Chinese A.I. is already chatting with millions" (2017)[URL]
- Lu, C-H, "Proceedings of the Intelligent Tutoring Systems (ITS) 2006 Lecture Notes in Computer Science: Vol 4053", pp.575~583 (2006), Springer
- Mauldin, M, "Chatterbots, tinymuds, and the turing test: Entering the loebner prize competition", Proceedings of the 11th National Conference on Artificial Intelligence (1994), AAAI Press
- McLaughlin, M. L, "Sage Series in Interpersonal Communication 3" (1984), Sage
- Nation, I. S. P, "Researching and analyzing vocabulary" (2011), Heinle Cengage Learning
- Shum, H, "From Eliza to XiaoIce: Challenges and opportunities with social chatbots", Frontiers of Information Technology & Electronic Engineering, 19(1), pp.10~26 (2018)
- Wang, Y, "Distance language learning: Interactivity and fourth-generation Internet-based video-conferencing", CALICO Journal, 21(2), pp.373~395 (2004)
- "Readability test tool" (2019)[URL]
- Weizenbaum, J, "ELIZA: A computer program for the study of natural language communication between man and machine", Communications of the Association for Computing Machinery, 9, pp.36~45 (1966)
- "Mitsuku wins Loebner Prize 2018" (2018)[URL]