we are very happy to share that we have been given the opportunity to share our work through two papers to be read during the 15th annual International Conference on Education and New Learning Technologies. The conference will be held in Palma de Mallorca from the 3rd till the 5th of July.
Utilising deep learning in Singapore primary school mathematical word problems is co-authored with Jing Zeng and James D Tan. its abstract reads:
In the regularly held Trends in International Mathematics and Science Study (TIMSS) and Programme for International Student Assessment (PISA) surveys, Singapore has performed consistently well. Singapore Math is a teaching approach originally developed by the country's Ministry of Education in the 1980s for its public schools. Since then, Singapore Math has been widely adopted in various forms around the world over the past twenty years.This paper describes an independent research project conducted by a pair of high school students under the mentorship of a senior research scientist from the National Institute of Education, Singapore, from April 2022 till March 2023. It describes a deep neural solver which the students designed and trained to solve Singapore mathematics word problems and to provide equations as explanation. In contrast to common approaches of plainly using the Math23K dataset, we translated the large dataset into English and inserted Singaporean Mathematics word problems that came from test papers and assessment books. By using an Encoder-Decoder model which uses recurrent neural networks (RNN), we fed the processed datasets into the model and evaluated the performance of the model based on different question types. Within the timeframe mandated by the research project, we were able to achieve an accuracy of the model for the Math23K dataset of 37.4%. The accuracy was lower for Singapore Mathematical word problems. The lower accuracy can be attributed to the model learning mainly Mathematical problems from a dataset derived from a non-Singaporean context, with the consequence that it was not able to sufficiently identify the new question types. The model performed best with “More than, Less than, As many as” questions, achieving an accuracy of 35%.
Music Mystery: learning music theory through escape room puzzles is co-authored with Kim Mai Truong and Yuxuan Wu. its abstract reads:
Music theory is essential for one to understand how a music piece is constructed. It is not only theoretical but also practical, providing the fundamentals for playing and composing music. For novices who are learning music, music theory poses a challenge due to the large corpus of potential information to be learned, and its technical nature. Thus, despite the benefits, novice learners can be demotivated and refrain from learning and understanding music theory, which is a challenge for educators. This paper describes an independent research study conducted by a pair of high school students under the mentorship of a senior research scientist from the National Institute of Education, Singapore, from April 2022 till March 2023. The study explored the use of escape room puzzles and instructional scaffolding in teaching novice learners about basic music theory. This study used Shaffer's (2005) epistemic frames in games as the basis for its experiment, combined with the use of technology-based scaffolding. The escape room, “Melody Mystery'', was made and conducted using Scratch, a website for creating games. Puzzles in the form of escape rooms were used due to their role-playing elements, which served to advance the in-game narrative of ‘novice-as-expert’. We examined how effective it was to engage and motivate novice learners when they were made to appropriate the role of an expert in music and solve problems using knowledge and skills from the domain. We found positive responses from participants’ attitudes toward music theory and their ability to retain knowledge of the subject, as well as evidence that suggests games can have significant effects on motivation in the learning process.
