Learning Tools Using ChatGPT in the Biochemistry Class: Creating Notes and Performance on Exams
Saved in:
| Title: | Learning Tools Using ChatGPT in the Biochemistry Class: Creating Notes and Performance on Exams |
|---|---|
| Language: | English |
| Authors: | Ana Roman (ORCID |
| Source: | Biochemistry and Molecular Biology Education. 2025 53(4):381-388. |
| Availability: | Wiley. Available from: John Wiley & Sons, Inc. 111 River Street, Hoboken, NJ 07030. Tel: 800-835-6770; e-mail: cs-journals@wiley.com; Web site: https://www.wiley.com/en-us |
| Peer Reviewed: | Y |
| Page Count: | 8 |
| Publication Date: | 2025 |
| Document Type: | Journal Articles Reports - Research |
| Education Level: | Higher Education Postsecondary Education |
| Descriptors: | Artificial Intelligence, Biochemistry, Science Instruction, Technology Uses in Education, Introductory Courses, Student Attitudes, Instructional Materials, Teaching Methods, Notetaking, Undergraduate Students, Science Tests |
| Geographic Terms: | Ohio |
| DOI: | 10.1002/bmb.21904 |
| ISSN: | 1470-8175 1539-3429 |
| Abstract: | ChatGPT has emerged as a popular choice in education that has transformed the experience for both teachers and students. This study investigates the performance of ChatGPT in aiding learning in the biochemistry classroom in two ways. We sought to determine how effective ChatGPT 3.5 was in generating study materials for an introductory biochemistry course. A lecture was delivered in class and transcribed. The resulting transcript was curated, then submitted to ChatGPT 3.5 to generate a summary, a set of notes, and an outline. Each artifact was verified and given to students to help prepare for a quiz. Students were asked about the use of AI-generated materials compared to other study materials. Results were bimodal for the AI-generated materials, with some students indicating that the materials were useful while others preferred traditional study materials such as the text or class notes. We also compared the performance of ChatGPT on open-note biochemistry exams that students had taken. The exams were completed by ChatGPT in two modes: with and without access to external tools. Performance metrics were used to evaluate ChatGPT performance and student responses. The results showed that ChatGPT was unable to pass the exams. This research provides valuable insights into the potential of ChatGPT in educational settings, highlighting strengths and limitations. The implications of these findings may inform the design of future AI-assisted tools and contribute to the ongoing discussions surrounding the integration of AI in education. |
| Abstractor: | As Provided |
| Entry Date: | 2025 |
| Accession Number: | EJ1478119 |
| Database: | ERIC |
| Abstract: | ChatGPT has emerged as a popular choice in education that has transformed the experience for both teachers and students. This study investigates the performance of ChatGPT in aiding learning in the biochemistry classroom in two ways. We sought to determine how effective ChatGPT 3.5 was in generating study materials for an introductory biochemistry course. A lecture was delivered in class and transcribed. The resulting transcript was curated, then submitted to ChatGPT 3.5 to generate a summary, a set of notes, and an outline. Each artifact was verified and given to students to help prepare for a quiz. Students were asked about the use of AI-generated materials compared to other study materials. Results were bimodal for the AI-generated materials, with some students indicating that the materials were useful while others preferred traditional study materials such as the text or class notes. We also compared the performance of ChatGPT on open-note biochemistry exams that students had taken. The exams were completed by ChatGPT in two modes: with and without access to external tools. Performance metrics were used to evaluate ChatGPT performance and student responses. The results showed that ChatGPT was unable to pass the exams. This research provides valuable insights into the potential of ChatGPT in educational settings, highlighting strengths and limitations. The implications of these findings may inform the design of future AI-assisted tools and contribute to the ongoing discussions surrounding the integration of AI in education. |
|---|---|
| ISSN: | 1470-8175 1539-3429 |
| DOI: | 10.1002/bmb.21904 |
