Abstract:

The student/teacher ratio has steadily increased especially with the increase in distance education participants or through massive open online courses (MOOC) [1]. In this context, the support and individual follow-up that a teacher can provide are difficult affecting the effective learning of students [2]. In addition, the lack of personalised attention can lead to dissatisfaction, drop-out and ultimately poor learning [2].

The solutions to these problems are to increase the number of teachers or to reduce the number of students per course. Both scenarios are challenging to achieve mainly for economic and organisational reasons. However, new technologies can mitigate the lack of personalised attention through the implementation of autonomous personal assistants. Among the personal assistants are chatbots, which are interactive chat agents that hold conversations in natural language through audio or text methods, understanding the user and sending a response based on pre-established rules. The main functions of chatbots are to provide personalised communication to users, to interact with them, to answer their questions and to address their concerns.

The benefits of using chatbots have already been proven, and in several sectors, it has been shown that they can lead to new growth and a better customer or user experience. However, the application of chatbots in the education sector has been studied from the perspective of implementation and potential use. However, there is a gap between academic studies regarding the suitability and acceptance of chatbot-based technology for automating services in higher education to improve student care. New evidence suggests that these programs have the potential to change the way students learn and seek information. In large-scale learning scenarios with more than one hundred students per teacher, chatbots are especially able to solve the problem of individual student support [1].

This study explores the use of chatbots that employ automatic learning to improve student attention in university courses. For this purpose, a chatbot with teacher assistance functions was implemented on a Moodle University platform. For the creation of the chatbot, group dynamics were carried out, where the students established the main functionalities to be implemented, as well as, to involve them in its design and personality. Once the chatbot was developed, it was used for two months to evaluate the degree of acceptance and satisfaction of the students with this technology.

The results of this study allow us to identify the most valuable functionalities that chatbots should incorporate, as well as to determine which aspects of the chatbot allow us to better predict the intention of use by students through a UTAUT2 Unified Theory of Acceptance, and Use of Technology model.

References:
[1] R. Winkler and M. Söllner, “Unleashing the Potential of Chatbots in Education: A State-Of-The-Art Analysis,” presented at the Academy of Management Annual Meeting (AOM), Chicago, USA, 2018.
[2] C. G. Brinton, R. Rill, S. Ha, M. Chiang, R. Smith, and W. Ju, “Individualization for Education at Scale: MIIC Design and Preliminary Evaluation,” IEEE Trans. Learning Technol., vol. 8, no. 1, pp. 136–148, Jan. 2015, doi: 10.1109/TLT.2014.2370635.

Keywords:

Chatbots, UTAUT2, personal assistance.