Developing an AI-based chatbot for practicing responsive teaching in mathematics

Lee, Dabae; Yeo, Sheunghyun

doi:10.1016/j.compedu.2022.104646

Cited by 61 publications

(46 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…9 Despite this limitation, chatbots have been used in diverse and creative ways, such as being learning partners, 18 to support exam preparation, 15 to answer frequently asked questions, 11,17 and as virtual students with misconceptions to support an authentic, meaningful, and open-ended teaching situation with preservice teachers. 10 Reviews in this area describe chatbots as educational resources growing in popularity and functionality 19−21 because more students have access to the Internet at home and at school, there is greater availability of intelligent learning technologies, and due to the digitalization of education accelerated by school closures due to the COVID-19 pandemic. 22 However, with this emerging resource, research gaps exist as there are few empirical studies investigating effective learning designs or learning strategies for this technology.…”

Section: ■ Introductionmentioning

confidence: 99%

“…Chatbots are used in educational settings, including Science, Technology, Engineering, and Mathematics (STEM) disciplines, because they have the potential to help students learn basic content in a responsive, interactive, and confidential way due to their real-time feedback, scalability, and increased student engagement . Chatbots have been used in different educational fields, such as mathematics education, nursing education, , and chemical education, − and especially in online courses. − The primary constraint on chatbot implementation has been the capabilities of the natural language processing, which limits the ability to have in-depth customized conversations, leading to the conclusion that chatbots can supplement, but not replace, classroom activities . Despite this limitation, chatbots have been used in diverse and creative ways, such as being learning partners, to support exam preparation, to answer frequently asked questions, , and as virtual students with misconceptions to support an authentic, meaningful, and open-ended teaching situation with preservice teachers .…”

Section: Introductionmentioning

confidence: 99%

“…8 Chatbots are used in educational settings, including Science, Technology, Engineering, and Mathematics (STEM) disciplines, because they have the potential to help students learn basic content in a responsive, interactive, and confidential way due to their real-time feedback, scalability, and increased student engagement. 9 Chatbots have been used in different educational fields, such as mathematics education, 10 nursing education, 11,12 and chemical education, 13−15 courses. 14−17 The primary constraint on chatbot implementation has been the capabilities of the natural language processing, which limits the ability to have in-depth customized conversations, leading to the conclusion that chatbots can supplement, but not replace, classroom activities.…”

Section: ■ Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Investigating the Use of an Artificial Intelligence Chatbot with General Chemistry Exam Questions

Clark

2023

J. Chem. Educ.

View full text Add to dashboard Cite

The artificial intelligence chatbot ChatGPT was used to answer questions from final exams administered in two general chemistry courses, including questions with closed-response format and with open-response format. For closed-response questions, ChatGPT was very capable at identifying the concept even when the question included a great deal of chemical symbolism. However, ChatGPT’s success at solving problems was only 44%, a value well below the class average of 69%. On open-response questions, ChatGPT’s responses displayed strong language processing ability with higher performance on questions that could be solved with more generalizable information compared to questions that required specific skills, especially when those topics or skills were primarily found in lecture. Incorrect responses and flawed explanations were often logically sound and would be persuasive to a novice. The chatbot is currently ill-equipped to provide reliable answers or explanations to students for many representative exam questions, but a potential use is to create assignments in which students analyze and improve ChatGPT’s responses.

show abstract

Section: ■ Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: ■ Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Investigating the Use of an Artificial Intelligence Chatbot with General Chemistry Exam Questions

Clark

2023

J. Chem. Educ.

View full text Add to dashboard Cite

show abstract

“…Khairy et al (2022) shared the value and the algorithmic characteristics of the use of assistive humanoid robots in the delivery of oral assessments. Lee and Yeo (2022) developed an AI-based chatbot that simulates open-ended, authentic interactions, for responsive teaching to promote arithmetic skills.…”

Section: Roboticsmentioning

confidence: 99%

Technology-enabled Learning in Digital Education: Research Areas and Prediction Trends of Learning Technologies for Authentic Assessments Practices

Lim

Gottipati

Cheong

2023

Preprint

View full text Add to dashboard Cite

This study aims to provide practical insights on the research areas and prediction trends of learning technologies that support authentic assessment practices in the digital education setting. Technology-enabled learning can be utilized to enhance assessment design in meaningful ways that resembles the professional work environment. Innovative technology-enabled assessment practices necessitate an understanding of the technologies at-hand, hence a disciplined inquiry is called upon into the multitude of technologies that define the landscape. The study looked to investigate the technology groups and research efforts within the field of learning technologies that were shaping digitally mediated authentic assessment practices. Using Horizon Report (HR), an annual education-based technology forecasting publication, as a reference, the study looked to evaluate if HR is a good proxy to predict the evolution of learning technologies in the said scape. Research distinguished four key learning technology groups, namely ubiquitous learning technology, adaptive learning technology, immersive learning technology, and learning object. Network analyses performed on the four technology groups identified key generalizable research themes that can be utilized for research focus. The study also found that HR is a useful tool to predict technology trends, as corroborated from bibliometric analyses, and detailed the composition and evolution of these trends. This study can help educators and researchers identify and decide promising potential areas for future research and/or investment focus.

show abstract

“…Chatbots use AI techniques such as machine learning (ML) and natural language processing (NLP) [5]- [8]. Today, chatbots are integrated into every business, including education [7], [9], banking [10], transportation [11], communication [12], [13], hospitals [14]- [16], and other services [17]. Likewise, in ecommerce sales and marketing [18], an intelligent knowledge-based conversational agent system to support customer service has been implemented [19].…”

Section: Introductionmentioning

confidence: 99%

Chatbot for Diagnosis of Pregnancy Disorders using Artificial Intelligence Markup Language (AIML)

Rahmatulloh

Ginanjar

Darmawan

et al. 2023

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

Artificial Intelligence has evolved in sophistication and widespread use. This study aims to create a chatbot application in the health sector regarding the early diagnosis of pregnancy disorders. Based on basic health research, only 44 percent of pregnant women know the danger signs of pregnancy. The chatbot application developed is expected to facilitate and increase knowledge for pregnant women about the danger signs of pregnancy, especially early diagnosis of pregnancy disorders. The chatbot application was developed with artificial intelligence technology based on Artificial Intelligence Markup Language with the question-answer concept using the Pandorabots framework. The test is carried out in two stages: functional and pattern matching. The functional testing uses the black-box testing method, and the pattern-matching test on the chatbot uses the sentence similarity and bigram methods based on user input and keywords similarity in the bot's knowledge base. The functional testing results show that the chatbot application runs well, with the eligibility criteria reaching 81.4% and the results of the keyword similarity test (pattern matching) are zero to one, in the sense that the value of one has the same similarity between user input and pattern. Meanwhile, the zero value has no similarities, so the bot will respond to it as free input. So it can be concluded that the bot can respond to user questions when the pattern and input have the same level of similarity.

show abstract

Developing an AI-based chatbot for practicing responsive teaching in mathematics

Cited by 61 publications

References 42 publications

Investigating the Use of an Artificial Intelligence Chatbot with General Chemistry Exam Questions

Investigating the Use of an Artificial Intelligence Chatbot with General Chemistry Exam Questions

Technology-enabled Learning in Digital Education: Research Areas and Prediction Trends of Learning Technologies for Authentic Assessments Practices

Chatbot for Diagnosis of Pregnancy Disorders using Artificial Intelligence Markup Language (AIML)

Contact Info

Product

Resources

About