Reverse SQL Question Generation Algorithm in the DBLearn Adaptive E-Learning System

Abstract

Using a traditional e-learning system, when teaching structured query language (SQL) queries in classical classrooms help instructors, to improve the students' SQL skills and learning effectiveness. However several problems in using e-learning as a teaching and learning assistant remain - such as difficulties in differences in learning ability and knowledge level. We solved these problems by applying an adaptation module to our e-learning system. However, we still found it required considerable effort to create enough exercises to make the adaptation effective enough. So, we developed a novel automatic question generating algorithm, named Reverse SQL Question Generation Algorithm (RSQLG), to automatically generate exercises (including both answer and question) from a source database. RSQLG reverses the traditional manual process used previously by instructors. Instead of creating questions and answers for them, RSQLG creates the answers first. The generated exercises are presented to students by applying question adaptation methodology based on student knowledge level in each supported learning objective. We evaluated the learning effectiveness of our approach by using outcome-based learning. After post-test to pre-test scores were compared, we found students using our system improved their scores by 26%. Consequently, the adaptive e-learning framework using RSQLG could be applied in any adaptive or traditional e-learning for a database course to benefit the instructors leading to less effort in exercise management and to improve the learning outcome from the students allowing as much practice as they need.