Tong Wan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Tong Wan has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Jacquelyn J. Chini
Department of Physics, University of Central Florida, Orlando, USA
9 shared publications - Erin K. H. Saitta
Department of Chemistry, University of Central Florida, Orlando, USA
8 shared publications Ashley A. Geraets
Department of Chemistry, University of Central Florida, Orlando, USA
7 shared publications- Constance M. Doty
Department of Physics University of Central Florida 4111 Libra Dr. 32816 Orlando FL
5 shared publications - Zhongzhou Chen
University of Central Florida
4 shared publications Christopher A. Nix
Department of Chemistry, University of Central Florida, Orlando, USA
3 shared publications
Latest Publications
- Open Access
- 17 August 2026
- Published by Springer Nature in Research in Science Education
- p. 1-20
Stretching the Applications of Simulator Rehearsal: Preparing Chemistry GTAs in Questioning Techniques
- 17 August 2026
- Published by Springer Nature in Research in Science Education
- p. 1-20
Open AccessStretching the Applications of Simulator Rehearsal: Preparing Chemistry GTAs in Questioning Techniques
- 1 January 2026
- Published by American Association of Physics Teachers (AAPT) in The Physics Teacher
- Vol. 64 (1) , 23-26
Using Skateboarding to Develop a Culturally Relevant Tutorial on Static Equilibrium
- 1 January 2026
- Published by American Association of Physics Teachers (AAPT) in The Physics Teacher
- Vol. 64 (1) , 23-26
Using Skateboarding to Develop a Culturally Relevant Tutorial on Static Equilibrium
- Open Access
- 9 July 2025
- Published by American Physical Society (APS) in Physical Review Physics Education Research
- Vol. 21 (2)
Characterizing discourse group roles in inquiry-based university science labs
Group work is commonly adopted in university science laboratories. However, student small-group discourse in university science labs is rarely investigated. We aim to bridge the gap in the literature by characterizing student discourse group roles in inquiry-based science labs. The instructional context for this study was a summer program hosted at a private research university in the eastern United States. The program was designed as a bridge program for matriculating students who were first generation and/or deaf or hard of hearing (DHH). Accommodations such as interpreters and technological tools were provided for DHH students. We analyzed 19 students’ discourse moves in five lab activities from the video recordings, resulting in a total of 48 student-lab units. We developed codes to describe student discourse moves: , and . Through a cluster analysis using the 48 student-lab units on quantified discourse moves, we identified four discourse styles, . The results show that individual students tended to demonstrate varying discourse styles in different lab activities; students’ discourse styles within the same groups tended to be aligned with their group members. By examining group members’ discourse styles in mixed-gender groups, we did not observe a difference in engagement levels between female and male students. DHH students in mixed hearing ability groups, however, were observed to have a lower level of engagement compared to their non-DHH group members. We discuss possible factors that may have contributed to the observations for genders and students with different hearing abilities. We also provide suggestions for promoting equitable small-group discourse in university science labs.
- 9 July 2025
- Published by American Physical Society (APS) in Physical Review Physics Education Research
- Vol. 21 (2)
Open AccessCharacterizing discourse group roles in inquiry-based university science labs
Group work is commonly adopted in university science laboratories. However, student small-group discourse in university science labs is rarely investigated. We aim to bridge the gap in the literature by characterizing student discourse group roles in inquiry-based science labs. The instructional context for this study was a summer program hosted at a private research university in the eastern United States. The program was designed as a bridge program for matriculating students who were first generation and/or deaf or hard of hearing (DHH). Accommodations such as interpreters and technological tools were provided for DHH students. We analyzed 19 students’ discourse moves in five lab activities from the video recordings, resulting in a total of 48 student-lab units. We developed codes to describe student discourse moves: , and . Through a cluster analysis using the 48 student-lab units on quantified discourse moves, we identified four discourse styles, . The results show that individual students tended to demonstrate varying discourse styles in different lab activities; students’ discourse styles within the same groups tended to be aligned with their group members. By examining group members’ discourse styles in mixed-gender groups, we did not observe a difference in engagement levels between female and male students. DHH students in mixed hearing ability groups, however, were observed to have a lower level of engagement compared to their non-DHH group members. We discuss possible factors that may have contributed to the observations for genders and students with different hearing abilities. We also provide suggestions for promoting equitable small-group discourse in university science labs.
- Top Cited PapersOpen Access
- 27 March 2025
- Published by American Physical Society (APS) in Physical Review Physics Education Research
- Vol. 21 (1)
Grading explanations of problem-solving process and generating feedback using large language models at human-level accuracy
[This paper is part of the Focused Collection in Artificial Intelligence Tools in Physics Teaching and Physics Education Research.] This study examines the feasibility and potential advantages of using large language models, in particular GPT-4o, to perform partial credit grading of large numbers of student written responses to introductory level physics problems. Students were instructed to write down verbal explanations of their reasoning process when solving one conceptual and two numerical calculation problems on two exams. The explanations were then graded according to a three-item rubric with each item graded as binary (1 or 0). We first demonstrate that machine grading using GPT-4o with no examples or reference answers can reliably agree with human graders in 70%–80% of all cases, which is equal to or higher than the level at which two human graders agree with each other. Two methods are essential for achieving this level of accuracy: (i) Adding explanation language to each rubric item that targets the errors of initial machine grading. (ii) Running the grading process 5 times and taking the most frequent outcome. Next, we show that the variation in outcomes across five machine grading attempts can serve as a grading confidence index. The index allows a human expert to identify ∼ 40 % of all potentially incorrect gradings by reviewing just 10%–15% of all responses with the highest variation. Finally, we show that it is straightforward to use GPT-4o to write a clear and detailed explanation of the partial credit grading outcome. Those explanations can be used as feedback for students, which will allow students to understand their grades and raise different opinions when necessary. Almost all feedback messages generated were rated three or above on a five-point scale by two instructors who had taught the course multiple times. The entire grading and feedback generating process costs roughly $5 per 100 student answers, which shows immense promise for automating labor-intensive grading process through a combination of machine grading with human input and supervision.
- 27 March 2025
- Published by American Physical Society (APS) in Physical Review Physics Education Research
- Vol. 21 (1)
Top Cited PapersOpen AccessGrading explanations of problem-solving process and generating feedback using large language models at human-level accuracy
[This paper is part of the Focused Collection in Artificial Intelligence Tools in Physics Teaching and Physics Education Research.] This study examines the feasibility and potential advantages of using large language models, in particular GPT-4o, to perform partial credit grading of large numbers of student written responses to introductory level physics problems. Students were instructed to write down verbal explanations of their reasoning process when solving one conceptual and two numerical calculation problems on two exams. The explanations were then graded according to a three-item rubric with each item graded as binary (1 or 0). We first demonstrate that machine grading using GPT-4o with no examples or reference answers can reliably agree with human graders in 70%–80% of all cases, which is equal to or higher than the level at which two human graders agree with each other. Two methods are essential for achieving this level of accuracy: (i) Adding explanation language to each rubric item that targets the errors of initial machine grading. (ii) Running the grading process 5 times and taking the most frequent outcome. Next, we show that the variation in outcomes across five machine grading attempts can serve as a grading confidence index. The index allows a human expert to identify ∼ 40 % of all potentially incorrect gradings by reviewing just 10%–15% of all responses with the highest variation. Finally, we show that it is straightforward to use GPT-4o to write a clear and detailed explanation of the partial credit grading outcome. Those explanations can be used as feedback for students, which will allow students to understand their grades and raise different opinions when necessary. Almost all feedback messages generated were rated three or above on a five-point scale by two instructors who had taught the course multiple times. The entire grading and feedback generating process costs roughly $5 per 100 student answers, which shows immense promise for automating labor-intensive grading process through a combination of machine grading with human input and supervision.
- Open Access
- 12 September 2024
- Published by American Association of Physics Teachers (AAPT)
- p. 97-101
Achieving Human Level Partial Credit Grading of Written Responses to Physics Conceptual Question using GPT-3.5 with Only Prompt Engineering
Large language modules (LLMs) have great potential for auto-grading student written responses to physics problems due to their capacity to process and generate natural language. In this explorative study, we use a prompt engineering technique, which we name "scaffolded chain of thought (COT)", to instruct GPT-3.5 to grade student written responses to a physics conceptual question. Compared to common COT prompting, scaffolded COT prompts GPT-3.5 to explicitly compare student responses to a detailed, well-explained rubric before generating the grading outcome. We show that when compared to human raters, the grading accuracy of GPT-3.5 using scaffolded COT is 20%-30% higher than conventional COT. The level of agreement between AI and human raters can reach 70%-80%, comparable to the level between two human raters. This shows promise that an LLM-based AI grader can achieve human-level grading accuracy on a physics conceptual problem using prompt engineering techniques alone.
- 12 September 2024
- Published by American Association of Physics Teachers (AAPT)
- p. 97-101
Open AccessAchieving Human Level Partial Credit Grading of Written Responses to Physics Conceptual Question using GPT-3.5 with Only Prompt Engineering
Large language modules (LLMs) have great potential for auto-grading student written responses to physics problems due to their capacity to process and generate natural language. In this explorative study, we use a prompt engineering technique, which we name "scaffolded chain of thought (COT)", to instruct GPT-3.5 to grade student written responses to a physics conceptual question. Compared to common COT prompting, scaffolded COT prompts GPT-3.5 to explicitly compare student responses to a detailed, well-explained rubric before generating the grading outcome. We show that when compared to human raters, the grading accuracy of GPT-3.5 using scaffolded COT is 20%-30% higher than conventional COT. The level of agreement between AI and human raters can reach 70%-80%, comparable to the level between two human raters. This shows promise that an LLM-based AI grader can achieve human-level grading accuracy on a physics conceptual problem using prompt engineering techniques alone.
- Top Cited PapersOpen Access
- 13 June 2024
- Published by American Physical Society (APS) in Physical Review Physics Education Research
- Vol. 20 (1) , 010152
Exploring generative AI assisted feedback writing for students’ written responses to a physics conceptual question with prompt engineering and few-shot learning
Instructor’s feedback plays a critical role in students’ development of conceptual understanding and reasoning skills. However, grading student written responses and providing personalized feedback can take a substantial amount of time, especially in large enrollment courses. In this study, we explore using GPT-3.5 to write feedback on students’ written responses to conceptual questions with prompt engineering and few-shot learning techniques. In stage I, we used a small portion () of the student responses on one conceptual question to iteratively train GPT to generate feedback. Four of the responses paired with human-written feedback were included in the prompt as examples for GPT. We tasked GPT to generate feedback for another 16 responses and refined the prompt through several iterations. In stage II, we gave four student researchers (one graduate and three undergraduate researchers) the 16 responses as well as two versions of feedback, one written by the authors and the other by GPT. Students were asked to rate the correctness and usefulness of each feedback and to indicate which one was generated by GPT. The results showed that students tended to rate the feedback by human and GPT equally on correctness, but they all rated the feedback by GPT as more useful. Additionally, the success rates of identifying GPT’s feedback were low, ranging from 0.1 to 0.6. In stage III, we tasked GPT to generate feedback for the rest of the students’ responses (). The feedback messages were rated by four instructors based on the extent of modification needed if they were to give the feedback to students. All four instructors rated approximately 70% (ranging from 68% to 78%) of the feedback statements needing only minor or no modification. This study demonstrated the feasibility of using generative artificial intelligence (AI) as an assistant to generate feedback for student written responses with only a relatively small number of examples in the prompt. An AI assistant can be one of the solutions to substantially reduce time spent on grading student written responses.- 13 June 2024
- Published by American Physical Society (APS) in Physical Review Physics Education Research
- Vol. 20 (1) , 010152
Top Cited PapersOpen AccessExploring generative AI assisted feedback writing for students’ written responses to a physics conceptual question with prompt engineering and few-shot learning
Instructor’s feedback plays a critical role in students’ development of conceptual understanding and reasoning skills. However, grading student written responses and providing personalized feedback can take a substantial amount of time, especially in large enrollment courses. In this study, we explore using GPT-3.5 to write feedback on students’ written responses to conceptual questions with prompt engineering and few-shot learning techniques. In stage I, we used a small portion () of the student responses on one conceptual question to iteratively train GPT to generate feedback. Four of the responses paired with human-written feedback were included in the prompt as examples for GPT. We tasked GPT to generate feedback for another 16 responses and refined the prompt through several iterations. In stage II, we gave four student researchers (one graduate and three undergraduate researchers) the 16 responses as well as two versions of feedback, one written by the authors and the other by GPT. Students were asked to rate the correctness and usefulness of each feedback and to indicate which one was generated by GPT. The results showed that students tended to rate the feedback by human and GPT equally on correctness, but they all rated the feedback by GPT as more useful. Additionally, the success rates of identifying GPT’s feedback were low, ranging from 0.1 to 0.6. In stage III, we tasked GPT to generate feedback for the rest of the students’ responses (). The feedback messages were rated by four instructors based on the extent of modification needed if they were to give the feedback to students. All four instructors rated approximately 70% (ranging from 68% to 78%) of the feedback statements needing only minor or no modification. This study demonstrated the feasibility of using generative artificial intelligence (AI) as an assistant to generate feedback for student written responses with only a relatively small number of examples in the prompt. An AI assistant can be one of the solutions to substantially reduce time spent on grading student written responses. - 1 March 2024
- Published by American Association of Physics Teachers (AAPT) in The Physics Teacher
- Vol. 62 (3) , 178-181
Using the Contrasting-Cases Approach to Improve Student Ability to Draw Conclusions from Measurement Data
Measurement uncertainty is a key concept in introductory physics lab courses. Research has demonstrated that students often struggle with grasping the concept a
- 1 March 2024
- Published by American Association of Physics Teachers (AAPT) in The Physics Teacher
- Vol. 62 (3) , 178-181
Using the Contrasting-Cases Approach to Improve Student Ability to Draw Conclusions from Measurement Data
Measurement uncertainty is a key concept in introductory physics lab courses. Research has demonstrated that students often struggle with grasping the concept a
- Open Access
Exploring Generative AI assisted feedback writing for students' written responses to a physics conceptual question with prompt engineering and few-shot learning
Instructor's feedback plays a critical role in students' development of conceptual understanding and reasoning skills. However, grading student written responses and providing personalized feedback can take a substantial amount of time. In this study, we explore using GPT-3.5 to write feedback to student written responses to conceptual questions with prompt engineering and few-shot learning techniques. In stage one, we used a small portion (n=20) of the student responses on one conceptual question to iteratively train GPT. Four of the responses paired with human-written feedback were included in the prompt as examples for GPT. We tasked GPT to generate feedback to the other 16 responses, and we refined the prompt after several iterations. In stage two, we gave four student researchers the 16 responses as well as two versions of feedback, one written by the authors and the other by GPT. Students were asked to rate the correctness and usefulness of each feedback, and to indicate which one was generated by GPT. The results showed that students tended to rate the feedback by human and GPT equally on correctness, but they all rated the feedback by GPT as more useful. Additionally, the successful rates of identifying GPT's feedback were low, ranging from 0.1 to 0.6. In stage three, we tasked GPT to generate feedback to the rest of the student responses (n=65). The feedback was rated by four instructors based on the extent of modification needed if they were to give the feedback to students. All the instructors rated approximately 70% of the feedback statements needing only minor or no modification. This study demonstrated the feasibility of using Generative AI as an assistant to generating feedback for student written responses with only a relatively small number of examples. An AI assistance can be one of the solutions to substantially reduce time spent on grading student written responses.
Open AccessExploring Generative AI assisted feedback writing for students' written responses to a physics conceptual question with prompt engineering and few-shot learning
Instructor's feedback plays a critical role in students' development of conceptual understanding and reasoning skills. However, grading student written responses and providing personalized feedback can take a substantial amount of time. In this study, we explore using GPT-3.5 to write feedback to student written responses to conceptual questions with prompt engineering and few-shot learning techniques. In stage one, we used a small portion (n=20) of the student responses on one conceptual question to iteratively train GPT. Four of the responses paired with human-written feedback were included in the prompt as examples for GPT. We tasked GPT to generate feedback to the other 16 responses, and we refined the prompt after several iterations. In stage two, we gave four student researchers the 16 responses as well as two versions of feedback, one written by the authors and the other by GPT. Students were asked to rate the correctness and usefulness of each feedback, and to indicate which one was generated by GPT. The results showed that students tended to rate the feedback by human and GPT equally on correctness, but they all rated the feedback by GPT as more useful. Additionally, the successful rates of identifying GPT's feedback were low, ranging from 0.1 to 0.6. In stage three, we tasked GPT to generate feedback to the rest of the student responses (n=65). The feedback was rated by four instructors based on the extent of modification needed if they were to give the feedback to students. All the instructors rated approximately 70% of the feedback statements needing only minor or no modification. This study demonstrated the feasibility of using Generative AI as an assistant to generating feedback for student written responses with only a relatively small number of examples. An AI assistance can be one of the solutions to substantially reduce time spent on grading student written responses.
- Open Access
- 15 October 2023
- Published by American Association of Physics Teachers (AAPT)
- p. 296-301
Physics Graduate Teaching Assistant Use of Error Framing in Recitations and Laboratories
Despite the positive gains towards student learning outcomes and engagement, active learning has been shown to potentially increase student anxiety due to a fear of negative evaluation. A pedagogical strategy proposed to mediate this issue is known as error framing; it asks instructors to encourage a perception of errors as being a natural part of the learning process. Previous work on this project investigated how graduate teaching assistants (GTAs) operationalized error framing during their training in a mixed-reality simulator but did not investigate their usage of it in their classrooms. This analysis characterizes the error framing statements made by GTAs during a set of classroom observations. We find that GTAs who employ error framing effectively avoid statements that might decrease student comfort and instead tend towards implicit, indirect strategies.
- 15 October 2023
- Published by American Association of Physics Teachers (AAPT)
- p. 296-301
Open AccessPhysics Graduate Teaching Assistant Use of Error Framing in Recitations and Laboratories
Despite the positive gains towards student learning outcomes and engagement, active learning has been shown to potentially increase student anxiety due to a fear of negative evaluation. A pedagogical strategy proposed to mediate this issue is known as error framing; it asks instructors to encourage a perception of errors as being a natural part of the learning process. Previous work on this project investigated how graduate teaching assistants (GTAs) operationalized error framing during their training in a mixed-reality simulator but did not investigate their usage of it in their classrooms. This analysis characterizes the error framing statements made by GTAs during a set of classroom observations. We find that GTAs who employ error framing effectively avoid statements that might decrease student comfort and instead tend towards implicit, indirect strategies.
- Open Access
- 5 July 2023
- Published by American Physical Society (APS) in Physical Review Physics Education Research
- Vol. 19 (2) , 020101
Impact of high-intensity training with a mixed-reality simulator on graduate teaching assistants use of questioning
Physics graduate teaching assistants (GTAs) are tasked with multifaceted teaching assignments, such as leading tutorials and inquiry-based laboratories, yet their professional development rarely includes opportunities to rehearse complex pedagogical skills or receive feedback on their teaching. In this study, physics GTAs practiced specific pedagogical skills during four sessions in a mixed-reality classroom simulator; here, we focus on GTAs’ use of a specific questioning strategy called “Stretch-It.” GTAs can apply Stretch-It by asking students to explain their logic (Explain Logic), either by explaining their work or providing evidence for their claim; or by asking students to take the content further (Follow-Up), either by applying it in an analogous situation or answering the initial question in another way. We found GTAs used all four types of Stretch-It subcategories during simulator sessions that incorporated facilitator feedback about their use of questioning. We also compared the use of Stretch-It questioning in the classroom for a pretraining semester cohort and the high-intensity simulator training cohort and found that the high-intensity cohort’s average use of Explain Logic questions in the observation immediately following the Stretch-It rehearsal was meaningfully higher than the pretraining cohort’s average use of Explain Logic. However, the high-intensity cohort’s use of Explain Logic is unstable, and values fall back within the pretraining average in subsequent classroom observations. We did not find a significant difference between the cohorts’ use of Follow-Up. We discuss the implications of our findings for science, technology, engineering, and medicine GTA professional development and the significance of providing feedback to GTAs about their teaching.
- 5 July 2023
- Published by American Physical Society (APS) in Physical Review Physics Education Research
- Vol. 19 (2) , 020101
Open AccessImpact of high-intensity training with a mixed-reality simulator on graduate teaching assistants use of questioning
Physics graduate teaching assistants (GTAs) are tasked with multifaceted teaching assignments, such as leading tutorials and inquiry-based laboratories, yet their professional development rarely includes opportunities to rehearse complex pedagogical skills or receive feedback on their teaching. In this study, physics GTAs practiced specific pedagogical skills during four sessions in a mixed-reality classroom simulator; here, we focus on GTAs’ use of a specific questioning strategy called “Stretch-It.” GTAs can apply Stretch-It by asking students to explain their logic (Explain Logic), either by explaining their work or providing evidence for their claim; or by asking students to take the content further (Follow-Up), either by applying it in an analogous situation or answering the initial question in another way. We found GTAs used all four types of Stretch-It subcategories during simulator sessions that incorporated facilitator feedback about their use of questioning. We also compared the use of Stretch-It questioning in the classroom for a pretraining semester cohort and the high-intensity simulator training cohort and found that the high-intensity cohort’s average use of Explain Logic questions in the observation immediately following the Stretch-It rehearsal was meaningfully higher than the pretraining cohort’s average use of Explain Logic. However, the high-intensity cohort’s use of Explain Logic is unstable, and values fall back within the pretraining average in subsequent classroom observations. We did not find a significant difference between the cohorts’ use of Follow-Up. We discuss the implications of our findings for science, technology, engineering, and medicine GTA professional development and the significance of providing feedback to GTAs about their teaching.