Effective Learning of Tax Regulations using Different Chatbot Techniques

Abstract

Teaching tax-related regulations have always been a challenge due to the inclusion of external variables that hinder the learning process, such as the high complexity of tax systems and legislation variability. Universities have sought different alternatives to support the teaching process both outside and inside the classroom, ranging from recreational activities to active learning. This article will show the experience resulting from using a chatbot to support learning in accounting students for the teaching of tax regulations related to the Chilean tax system, comparing two types of tools, on the one hand, a free conversation chatbot using natural language processing versus a rule-based chatbot driven by a decision tree. The experimentation process was carried out with 50 higher education students, divided into an experimental group and a control group, in two different courses. The results obtained demonstrated in both cases greater effectiveness of the use of the chatbot in learning the tax matter, both in the free conversation chatbot where the experimental group obtained a 15.7% improvement versus the control group that obtained a 1.05% improvement, as in the chatbot that applied decision tree where the experimental group obtained a 32% improvement versus the control group with 5.2%. Considering the complexity of the content in tax matters and the little innovation in the existing teaching subjects in the area and that the students improve learning using both chatbot tools compared to other learning techniques, is considered a relevant contribution to teaching innovation.

Interacting with educational chatbots: A systematic review

“…The teaching agent simply mimics a tutor by presenting scenarios to be discussed with students. In other studies, the teaching agent emulates a teacher conducting a formative assessment by evaluating students' knowledge with multiple-choice questions (Rodrigo et al, 2012;Griol et al, 2014;Mellado-Silva et al, 2020;. Moreover, it has been found that teaching agents use various techniques to engage students.…”

Contribuições das metodologias ativas de aprendizagem em contabilidade: uma revisão integrativa

“…As principais atividades para o desenvolvimento das habilidades pode ser mediante a adoção do método socrático, isso é, questionamentos aos estudantes durante a aula (Blankley et al, 2017); o uso de aulas invertidas (Brown et al, 2016); aprendizado cooperativo e colaborativo (Blankley et al, 2017); aplicação de estudos de caso para desenvolvimento da análise e discussão . E, com o avanço tecnológico, os docentes também podem adotar fóruns on-line, blogs, salas de bate papo, sistema de respostas, como o clickers, Kahoot, entre outros (Grávalos-Gastaminza et al, 2022;Krom, 2012;Mellado-Silva et al, 2020).…”

“…O feedback dos alunos indicou que a tarefa melhorou seu aprendizado de conhecimento técnico tributário, exigiu que fossem criativos e originais, encorajou-os a fazer ligações entre conceitos tributários relacionados e os motivou a usar os recursos de pesquisa de forma mais eficaz. Mellado-Silva et al (2020), com a aplicação de um chatbot para o ensino de regulamentos tributários do Chile, também verificaram sua eficácia em acordo com o melhor desempenho dos alunos.…”

Exploring the Potential Benefits and Risks of ChatGPT in Engineering Education

“…One potential benefit is the ability for ChatGPT to assist with generating and answering multiple choice questions, providing students with instant feedback, and allowing them to quickly assess their understanding of the material. This can be seen in the study " Effective learning of tax regulations using different chatbot techniques" by Mellado-Silva et al [27], which found that the use of AI in education led to improved student performance on multiple choice assessments. Furthermore, ChatGPT can potentially facilitate more dynamic discussions.…”