An Enhanced AI Chatbot to Facilitate Learning Performance in a Virtual 3D Chemistry Laboratory

To avoid the dangers brought about by students when operating unfamiliar chemical experiments, and to improve students’ understanding of the experimental procedures and safety of chemical experiments before they enter the laboratory, this study constructs a virtual 3D chemistry laboratory to facilitate active exploration of chemical concepts and procedural understanding through lifelike simulations, eliminating the need for physical materials and equipment and reducing costs and environmental impact associated with traditional physical chemistry laboratory. Moreover, this study presents an enhanced artificial intelligence chatbot (EAIC) that integrates the capabilities of ChatGPT and Rasa to assist teachers in guiding numerous students to promote autonomous learning performance in the virtual 3D chemistry laboratory concurrently. To confirm the effects of the virtual 3D chemistry laboratory with an EAIC as a virtual tutor, this study examines whether the experimental group using the laboratory with an EAIC and the control group using the laboratory without an EAIC differ in learning performance, learning mode satisfaction, and technology acceptance. Additionally, a usability questionnaire was used to investigate the experimental group’s perception of the EAIC’s suitability as an instructional aid tool within the virtual laboratory setting. Experimental results show that learners in the experimental group had significantly higher learning mode satisfaction, overall technology acceptance, and perceived usefulness of technology acceptance than those of the control group. However, there were no significant differences in learning performance and perceived ease of use, indicating that both groups have equal learning performance and friendly use perception in the user interfaces. Additionally, the experimental group’s learners expressed satisfaction with the EAIC’s interactions regarding ongoing conversation, ease of understanding, offering an appropriate amount of information, and high response speed, but suggested improving its context tracking, accuracy, and dialogue clarity during conversational processes. This study brings a significant advancement in computer-assisted chemistry education, demonstrating the potential benefits of a virtual 3D chemistry laboratory with the support of an EAIC in science education.

Authors

Institutions

Publication Details

Journal
Journal of Science Education and Technology
Published
2026-04-21
DOI
https://doi.org/10.1007/s10956-026-10319-3
Primary Topic
AI in Service Interactions
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

An Enhanced AI Chatbot to Facilitate Learning Performance in a Virtual 3D Chemistry Laboratory

C S Chen, Chieh-Ling Huang, Bo-Jin Chen
Journal of Science Education and Technology
AI in Service Interactions
article

An Enhanced AI Chatbot to Facilitate Learning Performance in a Virtual 3D Chemistry Laboratory

C S Chen, Chieh-Ling Huang, Bo-Jin Chen
article en

Abstract

To avoid the dangers brought about by students when operating unfamiliar chemical experiments, and to improve students’ understanding of the experimental procedures and safety of chemical experiments before they enter the laboratory, this study constructs a virtual 3D chemistry laboratory to facilitate active exploration of chemical concepts and procedural understanding through lifelike simulations, eliminating the need for physical materials and equipment and reducing costs and environmental impact associated with traditional physical chemistry laboratory. Moreover, this study presents an enhanced artificial intelligence chatbot (EAIC) that integrates the capabilities of ChatGPT and Rasa to assist teachers in guiding numerous students to promote autonomous learning performance in the virtual 3D chemistry laboratory concurrently. To confirm the effects of the virtual 3D chemistry laboratory with an EAIC as a virtual tutor, this study examines whether the experimental group using the laboratory with an EAIC and the control group using the laboratory without an EAIC differ in learning performance, learning mode satisfaction, and technology acceptance. Additionally, a usability questionnaire was used to investigate the experimental group’s perception of the EAIC’s suitability as an instructional aid tool within the virtual laboratory setting. Experimental results show that learners in the experimental group had significantly higher learning mode satisfaction, overall technology acceptance, and perceived usefulness of technology acceptance than those of the control group. However, there were no significant differences in learning performance and perceived ease of use, indicating that both groups have equal learning performance and friendly use perception in the user interfaces. Additionally, the experimental group’s learners expressed satisfaction with the EAIC’s interactions regarding ongoing conversation, ease of understanding, offering an appropriate amount of information, and high response speed, but suggested improving its context tracking, accuracy, and dialogue clarity during conversational processes. This study brings a significant advancement in computer-assisted chemistry education, demonstrating the potential benefits of a virtual 3D chemistry laboratory with the support of an EAIC in science education.

Journal of Science Education and Technology
National Chin-Yi University of Technology (TW), National Chengchi University (TW)
National Chengchi University
Quality Education
Openalex Percentile: Top 7%
AI in Service Interactions
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.