“Using a multiplatform chatbot as an online tutor in a university course.”
Abstract
Allowing students to ask questions in a university course is a crucial aspect of learning, which leads to increased learning effectiveness but also increased workload of the teaching staff. To reduce their workload, this paper presents the design of a chatbot for instantly answering students' questions on multiple common social platforms including Telegram, Facebook Messenger and Line. The chatbot can answer questions in natural language and commands. Once the teachers upload the necessary course-related information to an online database, the chatbot can answer questions on the course materials and course logistics (e.g., class schedule). The chatbot also supports a login system so as to provide answers according to different student profiles (e.g., schedule of their enrolled class and score dissemination). A survey on ten undergraduate computer science students showed that our chatbot can effectively act as an online tutor to reduce teachers' workload and will be a useful tool to be integrated into other e-learning platforms.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The study by Lee et al. (2020) reported high usability.
“| (Lee et al., 2020) | Peer agent, chatbot driven 10 | High usefulness, High usability | |”
From Interacting with educational chatbots: A systematic review (2023) · cites this paper as Lee et al., 2020
Most of the participants in Lee et al. (2020) agreed that the chatbot is a valuable educational tool.
“It turned out that most of the participants agreed that the chatbot is a valuable educational tool”
From Interacting with educational chatbots: A systematic review (2023) · cites this paper as Lee et al., 2020
Only one study pointed to high usefulness, namely Lee et al. (2020).
“Only one study pointed to high usefulness and subjective satisfaction (Lee et al., 2020), while the others reported low to moderate subjective satisfaction (Table 13).”
From Interacting with educational chatbots: A systematic review (2023) · cites this paper as Lee et al., 2020
Only one study pointed to subjective satisfaction, namely Lee et al. (2020).
“Only one study pointed to high usefulness and subjective satisfaction (Lee et al., 2020), while the others reported low to moderate subjective satisfaction (Table 13).”
From Interacting with educational chatbots: A systematic review (2023) · cites this paper as Lee et al., 2020
The study by Lee et al. (2020) reported high usefulness.
“| (Lee et al., 2020) | Peer agent, chatbot driven 10 | High usefulness, High usability | |”
From Interacting with educational chatbots: A systematic review (2023) · cites this paper as Lee et al., 2020
In most studies, a positive trend was observed toward an increase in the use of chatbots in future education.
“In general, in most studies, a positive trend was observed toward an increase in the use of chatbots in future education (Pereira et al., 2019; Lee et al., 2020; Chuah and Kabilan, 2021; Fidan and Gencel, 2022; Khalil and Rambech, 2022; Mendoza et al., 2022).”
From Implementing the bashayer chatbot in Saudi higher education: measuring the influence on students' motivation and learning strategies (2023) · cites this paper as Lee et al., 2020
Providing feedback and stimulating the interaction cycle that supports social presence are important factors in active engagement with the chatbot learning environment.
“Providing feedback and stimulating the interaction cycle that supports social presence are important factors in active engagement with the chatbot learning environment (Lee et al., 2020; Huang et al., 2021; Kohnke, 2022; Mendoza et al., 2022).”
From Implementing the bashayer chatbot in Saudi higher education: measuring the influence on students' motivation and learning strategies (2023) · cites this paper as Lee et al., 2020
Cites
Students' questions: a potential resource for teaching and learning science
Chin, C., & Osborne, J. (2008) · Studies in Science Education · doi:10.1080/03057260701828101 · Cited by 747 · see citing works
Learning in Science: A Comparison of Deep and Surface Approaches
Chin, C., & Brown, D. E. (2000) · Journal of Research in Science Teaching · doi:10.1002/(sici)1098-2736(200002)37:2 · Cited by 499 · see citing works
Student Passivity: A Study of Question Asking in K-12 Classrooms
Good, T. L., Slavings, R. L., Harel, K. H., et al. (1987) · Sociology of Education · doi:10.2307/2112275 · Cited by 202 · see citing works
The Role of Chatbots in Formal Education
Molnár, G., & Szűts, Z. (2018) · IEEE International Symposium on Intelligent Systems and Informatics (SISY) · doi:10.1109/sisy.2018.8524609 · Cited by 198 · see citing works
Freudbot: An Investigation of Chatbot Technology in Distance Education
Heller, B., Proctor, M., Mah, D., Jewell, L. M., & Cheung, B. (2005) · EdMedia: World Conference on Educational Media and Technology · Cited by 117 · see citing works
Harper, K., Etkina, E., & Lin, Y. (2003) · Journal of Research in Science Teaching · doi:10.1002/tea.10111 · Cited by 104 · see citing works
The Question-Driven Classroom: Student Questions as Course Curriculum in Biology
Shodell, M. (1995) · The American Biology Teacher · doi:10.2307/4449992 · Cited by 87 · see citing works
A Pilot Study Integrating an AI-driven Chatbot in an Introductory Programming Course
Verleger, M., & Pembridge, J. (2018) · 2018 IEEE Frontiers in Education Conference (FIE) · doi:10.1109/fie.2018.8659282 · Cited by 86 · see citing works
Artificial intelligence technologies for personnel learning management systems
Nenkov, N., Dimitrov, G., Dyachenko, Y., & Koeva, K. (2016) · IEEE International Conference on Intelligent Systems · doi:10.1109/is.2016.7737420 · Cited by 48 · see citing works
Murad, D. F., Iskandar, A. G., Fernando, E., Octavia, T. S., & Maured, D. E. (2019) · International Conference on Information Technology, Computer, and Electrical Engineering · doi:10.1109/icitacee.2019.8904311 · Cited by 22 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Interacting with educational chatbots: A systematic review
Kuhail, M. A., Alturki, N., Alramlawi, S., & Alhejori, K. (2023) · Education and Information Technologies · doi:10.1007/s10639-022-11177-3 · Cited by 841 · see citing works
Al-Abdullatif, A. M. (2023) · Education Sciences · doi:10.3390/educsci13111151 · Cited by 102 · see citing works
Yusuf, H., Money, A., & Daylamani-Zad, D. (2025) · Educational technology research and development · doi:10.1007/s11423-025-10447-4 · Cited by 112 · see citing works
Al-Abdullatif, A. M., Al-Dokhny, A. A., & Drwish, A. M. (2023) · Frontiers in Psychology · doi:10.3389/fpsyg.2023.1129070 · Cited by 80 · see citing works
“These studies have been carried out in different educational contexts and learning environments, including distance learning (Kohnke, 2022), online learning (Lee et al., 2020; Troussas et al., 2020; Mendoza et al., 2022), mobile learning (Troussas et al.”
Background
- Authors
- Lee, L.-K., Fung, Y.-C., Pun, Y.-W., Wong, K.-K., Yu, M. T.-Y., & Wu, N.-I.
- Affiliations
- Hong Kong Metropolitan University (HK)
- Hong Kong Polytechnic University (HK)
- Venue
- 2020 International Symposium on Educational Technology (ISET)
- Publisher
- IEEE
- Published
- 2020-08
- Pages
- 53-56
- OpenAlex
- W3092639874
- Cited by
- 57
- References
- 10
- Citations by year
- 2026: 3 · 2025: 13 · 2024: 7 · 2023: 17 · 2022: 12 · 2021: 5
- FWCI
- 3.24
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- International Symposium on Educational Technology (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
- Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
- Physical Sciences › Computer Science › Artificial Intelligence › AI in Service Interactions
- Keywords
- chatbots, online tutoring, student question answering, teacher workload reduction, telegrams, Facebook Messenger, lines, natural language question answering, online learning, university courses
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
