TY - JOUR
T1 - Optimizing Database Query Learning
T2 - 2024 ASEE Annual Conference and Exposition
AU - AlRabah, Abdulrahman
AU - Yang, Sophia
AU - Alawini, Abdussalam
N1 - Publisher Copyright:
© American Society for Engineering Education, 2024.
PY - 2024/6/23
Y1 - 2024/6/23
N2 - In database education research, numerous common error types and overarching learning hurdles have been identified among learners, with a predominant focus on syntax errors. However, there has been a noticeable gap in the study and categorization of semantic errors, which are equally critical for students' learning and proficiency in database systems. Our study aims to explore this gap and contribute to the educational domain by investigating the potential of integrating the advanced capabilities of a Generative Pre-Trained Transformer (GPT) model with an existing feedback system to enhance the detection and feedback of semantic errors in student submissions of SQL queries. We have utilized diverse datasets of student submissions, which were employed to fine-tune our GPT models. This tailored training process has enabled the models to better recognize and highlight semantic errors, while simultaneously providing constructive and meaningful feedback. Preliminary results from our research are highly encouraging, demonstrating advancements and highlighting the potential of large language models in database learning. By integrating these state-of-the-art computational tools into the learning environment, our study lays the groundwork for the creation of intelligent systems that offer nuanced and context-aware feedback. Such systems have the potential to enhance the educational experience and support available to students.
AB - In database education research, numerous common error types and overarching learning hurdles have been identified among learners, with a predominant focus on syntax errors. However, there has been a noticeable gap in the study and categorization of semantic errors, which are equally critical for students' learning and proficiency in database systems. Our study aims to explore this gap and contribute to the educational domain by investigating the potential of integrating the advanced capabilities of a Generative Pre-Trained Transformer (GPT) model with an existing feedback system to enhance the detection and feedback of semantic errors in student submissions of SQL queries. We have utilized diverse datasets of student submissions, which were employed to fine-tune our GPT models. This tailored training process has enabled the models to better recognize and highlight semantic errors, while simultaneously providing constructive and meaningful feedback. Preliminary results from our research are highly encouraging, demonstrating advancements and highlighting the potential of large language models in database learning. By integrating these state-of-the-art computational tools into the learning environment, our study lays the groundwork for the creation of intelligent systems that offer nuanced and context-aware feedback. Such systems have the potential to enhance the educational experience and support available to students.
UR - http://www.scopus.com/inward/record.url?scp=85202051131&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85202051131&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:85202051131
SN - 2153-5965
JO - ASEE Annual Conference and Exposition, Conference Proceedings
JF - ASEE Annual Conference and Exposition, Conference Proceedings
Y2 - 23 June 2024 through 26 June 2024
ER -