The Impact of Chatbots Using Concept Maps on Correction Outcomes--A Case Study of Programming Courses

Autor/inn/en	Kuo, Yu-Chen; Chen, Yun-An
Titel	The Impact of Chatbots Using Concept Maps on Correction Outcomes--A Case Study of Programming Courses
Quelle	In: Education and Information Technologies, 28 (2023) 7, S.7899-7925 (27 Seiten)Infoseite zur Zeitschrift PDF als Volltext Verfügbarkeit
Zusatzinformation	ORCID (Kuo, Yu-Chen)
Sprache	englisch
Dokumenttyp	gedruckt; online; Zeitschriftenaufsatz
ISSN	1360-2357
DOI	10.1007/s10639-022-11506-6
Schlagwörter	Programming; Artificial Intelligence; Computer Science Education; Misconceptions; Concept Formation; Teaching Methods; Computer Software; Aptitude; Technical Support; Error Correction; Units of Study; Tests; Failure; Individualized Instruction; Instructional Effectiveness; Scores; Concept Mapping; Case Studies + Suchen Sie Ihr Suchwort? Programmierung; Künstliche Intelligenz; Computer science lessons; Informatikunterricht; Missverständnis; Concept learning; Begriffsbildung; Teaching method; Lehrmethode; Unterrichtsmethode; Eignung; Korrektur; Lerneinheit; Examination; Prüfung; Examen; Individualisierender Unterricht; Unterrichtserfolg; Concept Map; Case study; Fallstudie; Case Study
Abstract	With the development of science and technology, the demand for programmers has increased. However, learning computer programs is not an easy task. It might cause a significant impact on programming if misconceptions exist at the beginning of the study. Hence, it is important to discover and correct them immediately. Chatbots are effective teaching aids, they can assist students in eliminating misconceptions. They also assist teachers to instruct students according to their aptitude, which teachers found it hard to accomplish without technical supports when teaching in large classes. Therefore, this experiment uses chatbots to assist learners in the correction phase. We consider that learners who failed unit quizzes might have misunderstandings in programming concepts. We believe chatbots can teach according to individual misunderstandings and give correct responses to their unclear concepts. It is more effective than traditional teaching methods. In addition, to prevent human-computer interaction barriers, such as picking wrong keywords and giving plausible replies, or learners not being able to express their problems clearly, this experiment also adds concept maps to the chatbots' dialogue, to work as the dialogue structure for each chatbot. The maps help the chatbots to explain concepts in each unit systematically and logically. The chatbots give questions according to the concepts on the concept maps and ask learners to reply with their answers. An ANCOVA test investigated students' scores. Result showed the "p"-value is below 0.001, indicating that the group using concept map chatbots has better correction effects than the other group using only concept maps. (As Provided).
Anmerkungen	Springer. Available from: Springer Nature. One New York Plaza, Suite 4600, New York, NY 10004. Tel: 800-777-4643; Tel: 212-460-1500; Fax: 212-460-1700; e-mail: customerservice@springernature.com; Web site: https://link.springer.com/
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2024/1/01