(Press-News.org) By Jovina Ang
SMU Office of Research – “Giving students immediate and frequent feedback makes online learning more effective,” Associate Professor Ouh Eng Lieh told the Office of Research.
However, based on how most online lessons are designed, questions could not be answered nor doubts clarified until students meet their instructor in the following face-to-face class.
The time delay of a few days to a few weeks can impede student learning as it might make it difficult for students to catch up and understand the subsequent topics in the course.
Learning also does not occur until the knowledge gained is stored in long‐term memory.
The Cognitive Load Theory (CLT) states that for short-term knowledge to be committed to long-term memory, there must be effective cognitive load management, repeated reinforcements and clarification of doubts.
“That’s why providing timely feedback is vital for maintaining a seamless and effective student learning experience. It also helps the student to manage the cognitive load and learn,” Professor Ouh explained to the Office of Research.
He added: “It has been found that reflection prompts, which are essentially reminders to get students to reflect and journal their learnings, can significantly improve learning by getting students to retain and apply what they have learned. Additionally, by leveraging ChatGPT, we can evaluate the degree of understanding by comparing what the student has written to the context or the topic of the lesson.”
“With these in mind, we wanted to develop a learning tool that can provide personalised prompts so that students could either have their questions answered or doubts clarified as they go through their online lesson. This tool, which we have fondly named ‘Prompt Tutor’, will also be programmed to assign additional exercises or generate a quiz for students to hone their learning,” Professor Ouh elaborated.
“And to the best of our knowledge, we believe that this will be the very first Prompt Tutor to be developed in Singapore for teaching computing courses in tertiary institutions,” Professor Ouh went on.
The research
Professor Ouh’s project is funded by an MOE Tertiary Education Research Fund (TRF) grant. An expected three years is needed to develop a fully functioning Prompt Tutor and conduct the experimental research.
He is collaborating with Associate Professor Tan Kar Way and Assistant Professor Lo Siaw Ling, both of whom are from Singapore Management University (SMU), as well as Dr. Lin Feng from Singapore University of Social Sciences (SUSS).
The research builds on Professor Ouh’s previous work where he has successfully developed a Doubt Identification Machine Learning Model to single out doubts from written reflections.
The integration of Prompt Tutor to SMU’s ITSS (Interactive Tutorial Software System) makes it possible for the research team to engineer real time feedback by providing the context to the machine learning algorithms.
The initial part of the research project entails developing a sufficiently accurate Prompt Tutor – essentially a Prompt Tutor that can provide at least 90 percent accurate responses to the student queries or detect doubts in the written reflections.
A total of 80 SMU students enrolled in introductory programming courses will be recruited to participate in the research project. 40 students will be exposed to the Prompt Tutor while the remainder 40 will not be.
There are four steps in the research methodology.
Step 1: Students will be required to watch a five-minute video and write a reflection on what they have learnt.
Step 2: With the use of the Doubt Identification Machine Learning Model, the Prompt Tutor will be programmed to detect doubts or inaccuracies in the student reflections.
Step 3: The Prompt Tutor will then evaluate the students’ written work by checking against the context and accuracy of the topic of the lesson. If any doubt or inaccuracy is detected, the Prompt Tutor will notify the student by sending a personalised prompt such as asking the student a follow-up question for him/her to further reflect and learn.
Step 4: If no inaccuracy is detected, the Prompt Tutor will either prompt the student with more exercises or generate a quiz to test understanding.
Implications of the research
This research has wide ranging applications beyond the teaching of Computer Science or Information Systems courses.
Given that the development of the Prompt Tutor is based on CLT, and therefore, discipline agnostic, its use can be easily extended to the teaching in fields such as Social Science, Medicine, and even languages.
Other than benefiting the students, the Prompt Tutor can benefit instructors – by reducing the time spent on student consultation.
END
Innovating learning with ChatGPT-based Prompt Tutor
2024-05-31
[Attachments] See images for this press release:
ELSE PRESS RELEASES FROM THIS DATE:
Moving beyond cubicles: How an active workplace design can drive workers’ behaviors
2024-05-31
Ishikawa, Japan -- Physical inactivity and sitting for prolonged hours are highly prevalent among office-based workers, known to be resulting in various health risks and economic constraints. However, to reduce sedentary time and increase physical activity, health promotion interventions alone are insufficient. The design of workplaces should also be considered to promote interactive behavior among workers.
Many models, such as the socio-ecological model, show how multiple factors interact to influence workers' active and sedentary behaviors. These models specifically magnify the impact of workplace environments in shaping these behaviors. Several studies ...
Breakthrough in using bispecific antibodies for solid tumors
2024-05-31
Professor Seung-Woo Lee and PhD candidate Kun-Joo Lee from the Department of Life Sciences at Pohang University of Science and Technology (POSTECH), in collaboration with NeoImmuneTech Director Donghoon Choi and Professors Dae Hee Kim and Sun Shim Choi from Kangwon National University, have revealed a groundbreaking method to significantly enhance the efficacy of bispecific antibody therapies in treating solid tumors. Their findings were published on May 13 in “Cell Reports Medicine”, an international journal of healthcare research.
Bispecific antibodies, which can simultaneously bind to two different ...
Fjords are effective carbon traps regardless of oxygen levels
2024-05-31
The fjords on Sweden’s west coast act as effective carbon traps regardless of whether the bottom water is oxygen-rich or not. This is the conclusion of a new study with researchers from the University of Gothenburg.
Large quantities of plant parts sink to the bottom of fjords on the Swedish west coast where they form sediment. This buries organic carbon, which would otherwise contribute to ocean acidification and the greenhouse effect. When the plant parts are exposed to oxygen and other substances, the organic carbon begins to decompose into inorganic carbon, which can be dissolved into carbonic acid in the water. Research ...
Korea University College of Medicine’s team predict hearing conditions in vestibular schwannoma patients using radiomics
2024-05-31
Korea University College of Medicine’s Team Predict Hearing Conditions in Vestibular Schwannoma Patients Using Radiomics
A recent study demonstrates that radiomics imaging analysis can effectively forecast the hearing status of patients with vestibular schwannoma patients. Since treatment methods, such as surgery or active surveillance, vary for these patients based on tumor size and hearing condition, predicting hearing status is crucial in planning and determining the appropriate treatment.
The research team led by Professor June Choi from the Department ...
European Academy of Sciences honors Rice’s Pol Spanos with prestigious award
2024-05-31
HOUSTON – (May 31, 2024) – For his “exceptional contributions to the field of dynamics,” Pol Spanos, the Lewis B. Ryon Professor of Mechanical and Civil Engineering at Rice University, has been awarded the 2024 Blaise Pascal Medal in Engineering by the European Academy of Sciences.
Spanos, who joined the Rice faculty in 1984, was recognized for his “theoretical insights, ranging from equivalent linearization to statistical quadratization, which have significantly advanced our understanding of structural behavior. These insights have not only led to more accurate predictions but have also empowered engineers ...
Rice’s Jamie Padgett wins Charles Martin Duke Lifeline Earthquake Engineering Award
2024-05-31
HOUSTON – (May 31, 2024) – Jamie Padgett, the Stanley C. Moore Professor in Engineering and chair of civil and environmental engineering at Rice University, has received the 2024 Charles Martin Duke Lifeline Earthquake Engineering Award from the American Society of Civil Engineers (ASCE).
Padgett was recognized for her “contributions to fragility, risk and resilience modeling of multimodal transportation systems and their infrastructure components when subjected to earthquakes and other hazards.”
Her ...
Sleep moderates the link between bullying and suicide in teens
2024-05-31
DARIEN, IL – A new study to be presented at the SLEEP 2024 annual meeting found that sleep duration significantly moderates the association between bullying and suicide attempts among adolescents in the U.S.
The study revealed that 15% of adolescents reported they were bullied at school, and 16% were bullied electronically; 10.2% reported they had attempted suicide during the past year; and 77.3% did not adhere to sleep duration recommendations. Adolescents who reported 4 hours of sleep or less per night were two times as likely to attempt suicide, and sleep duration significantly moderated the association between bullying ...
AI-controlled stations can charge electric cars at a personal price
2024-05-31
As more and more people drive electric cars, congestion and queues can occur when many people need to charge at the same time. A new study from Chalmers University of Technology in Sweden shows how AI-controlled charging stations, through smart algorithms, can offer electric vehicle users personalised prices, and thus minimise both price and waiting time for customers. But the researchers point to the importance of taking the ethical issues seriously, as there is a risk that the artificial intelligence exploits information from motorists.
Today's commercial ...
The world’s most powerful anti-fungal chemistries cause fungal pathogens to self-destruct
2024-05-31
Scientists have discovered that the most widely-used class of antifungals in the world cause pathogens to self-destruct. The University of Exeter-led research could help improve ways to protect food security and human lives.
Fungal diseases account for the loss of up to a quarter of the world’s crops. They also pose a risk to humans and can be fatal for those with weakened immune systems.
Our strongest "weapon" against fungal plant diseases are azole fungicides. These chemical products account for to a quarter of the world agricultural ...
Could the world famous Roman Baths help scientists counter the challenge of antibiotic resistance?
2024-05-31
The world-famous Roman Baths are home to a diverse range of microorganisms which could be critical in the global fight against antimicrobial resistance, a new study suggests.
The research, published in the journal The Microbe, is the first to provide a detailed examination of the bacterial and archaeal communities found within the waters of the popular tourist attraction in the city of Bath (UK).
Scientists collected samples of water, sediment and biofilm from locations within the Roman Baths complex including the King’s Spring (where the waters reach around 45°C) and the Great Bath, where the temperatures ...