Other Projects 

Abstract:

Chatbots, also known as conversational agents, are increasingly popular in education and are one of the most useful Artificial Intelligence (AI) technologies that can be integrated into various aspects of education. We propose a project to develop a chatbot to support Singapore MOE K-12 students in learning Computing and evaluate its effectiveness on students' learning. The project will develop new insights, adds to the current theoretical understandings, and enriches international literature in the research field of education (technology) and artificial intelligence. The project will also demonstrate rigorous innovation by developing a chatbot that serves as a learning support tool in a form of agent-augmented intervention to help students to have a better understanding of computing concepts. The chatbot will serve a learning role in supporting students by providing instant feedback to students' queries related to the course topics. The dataset for the chatbot will be derived from a list of frequently asked questions about the topic that is developed by the teachers and discussed with the researchers. To investigate the students' perception of the use of chatbot for learning and the effectiveness of using agent-based learning, we will conduct a quasi-experimental study. Pre- and post-survey instruments will include the use of the Technology Acceptance Model on the perception of the chatbot and students' content knowledge of the topic along with open-ended questions. Analysis of quantitative data will use descriptive and inferential statistics while qualitative data will thematically analysed through coding. Participants in the study will include 70 upper secondary and Junior college students taking O and A level Computing subject. The project is helmed by an inter-disciplinary research team made of members from National Institute of Education, Computer Science and Engineering and MOE bringing in their expertise in education research, AI, software engineering, and classroom intervention design. 

Funding body: MOE

Lead PI: Dr Khor Ean Teng Karen

Co-PIs: Dr Vidya Sudarson, Dr Shen Zhiqi

Collaborators: Dr Seow Sen Kee, Peter, Dr Koh Ruilin, Elizabeth, Mr Gi Soong Chee

Abstract:

We propose SingaKids Pic2Speak - a picture-prompted multilingual virtual tutor for Singaporean students in primary 1 and primary 2 to practice their oral skills in MTL (see Figure 1). In question generation mode, SingaKids Pic2Speak can generate question answer pairs from a picture so teachers can select suitable ones for students to practice. In dialogue mode, these teacher selected question answer pairs can also be used in to prompt students with both the picture and question to elicit spoken answers. SingaKids Pic2Speak will evaluate the student's response in terms of content accuracy, grammatical correctness, and oral delivery (e.g. pronunciation, fluency) and give corresponding feedback. In addition, the engagement level of the student will also be assessed through the speech signal. By considering both engagement and capability, we can preposition recommendations and intervention strategies to increase student learning outcome and interest. The technical challenges of this grand challenge stem from data sparsity for technology deployment needs, including under-resourced languages, child usage in the education context, and processing of pictorial drawings. We will empirically fill in these gaps in academic research, which focuses largely on adults speaking American English, applications used by adults, and processing photographic images in computer vision. As far as we know, few scientists have investigated all these gaps empirically. We use hybrid AI as an overarching technical framework to tackle these real-world challenges. We will exploit domain knowledge from education experts to sharpen the solution space to reduce entropy of unseen scenarios (e.g. leveraging on expected error patterns in Singapore's English dominant multilingual landscape), integrate classic parse trees in linguistics and neural representations to address multilingual challenges, combine high level visual understanding (e.g. scene graphs) with low level semantics (e.g. image recognition) when adapting pre-trained models to work well on pictorial drawings with domain data, and take advantage of adversarial adaptation and acousticphonetics insights to address sparsity challenges of child data. We will also develop SingaKids-VQAP, a multilingual dataset for visual question, answer, and paraphrasing to better anchor these targeted technical endeavours. We will investigate these scientific endeavours by building upon our rich suite of background IPs and data assets in multilingual speech and language technology, which have led to recent commercial spin-offs (e.g. nomopai, KiteSense) and a multitude of government deployments (e.g. Whole of Government deployment for SG Translate, Malay and Tamil speech synthesis and evaluation at MOE SLS and iMTL, English speech evaluation deployment at SEAB, amongst numerous confidential deployments). Our team is skilled in efficient data modelling for translation and deployment needs. In particular, we exploit deep learning integrated with domain knowledge modelling to achieve high performance with minimal data usage. Such efforts have won us numerous local and international awards. We also have expertise in constructing and executing protocols for data collection, curation, annotation and analysis for real-world deployment to service partners and clients from education, healthcare, and defence sectors. In addition, we have strong backing in the local ecosystem from both commercial collaborators (e.g. Ednovation, NovoLearning) and public partners (e.g. SEAB) to jointly construct multimodal data assets, adopt our technology to enhance services, and spin-off companies. The total value-add from this project to these collaborators is estimated to be S$5.25 M/yr.

Funding body: AI Singapore - AI in Education Grand Challenge

Lead PI: Dr Nancy F. Chen

Co-PIs: Ms Suryani Binte Atan, Assoc Prof Seetha Lakshmi, Dr Tan Hui Li, Dr Dong Minghui, Asst Prof Zhang Hanwang, Assoc Prof Kan Min Yen, Assoc Prof Chng Eng Siong, Dr Wong Lung Hsiang, Dr Sun He, Dr Goh Hock Huan, Dr Khor Ean Teng Karen

Collaborators: Mr Richard Yen, Mr Martijn Enter, Dr Kang Mei-Ling

Abstract: 

With four official languages, the linguistic environment of Singapore is globally unique, with rich, inter-generational bilingualism in diverse languages, with diverse writing systems. This landscape provides unique advantages for Singapore’s progress in an increasingly globalised world. It also presents unique challenges in education, as teaching practices established in monolingual communities (like the US, the UK and Australia) may be poorly suited to the needs of Singapore’s bilingual learners. For this reason, it is critical to conduct investigations into how language and literacy develop within Singapore’s own bilingual communities, in order to support the educational needs of future generations. The lack of global research into early bilingualism means that Singaporeans do not have good guidance about how best to support children’s language needs in early care contexts and the pre-school years. Similarly, a lack of research into bilingual reading development means that dyslexia diagnosis and support is not tailored to the needs of Singaporeans whose linguistic experience may generate different patterns of strengths and weaknesses in the early reading years.

This research will evaluate how different patterns of exposure influence bilingual and biliterate language development in three research streams. (Birth to 2 years). We will record language spoken around infants and toddlers in the home, and evaluate how it contributes to the sensitivity, flexibility, and speed of toddlers’ aural-language skills. (pre-K to Grade 1). We will investigate the link between early language skills and learning to read, in a group of children evaluated for their early aural and pre-reading skills pre-kindergarten, and their reading and brain network connectivity after school entry.

Funding body: National Research Foundation


Lead PI: Asst Prof Suzy Styles
Co-PI: Dr Beth O'Brien (study lead), Prof Annabel Chen, A/P Justin Dauwels (TU Delft)

Mathematics well-being refers to a multidimensional construct encompassing cognitive health and socio-emotional well-being, particularly within the context of mathematical learning and engagement. Cognitive health in mathematics well-being pertains to the optimal cognitive functioning and processes involved in mathematical thinking, problem-solving, and skill acquisition while socio-emotional well-being involves the psychological and emotional dimensions of individuals' experiences in learning and engaging with mathematics (Pekrun et al., 2007). A comprehensive understanding of mathematics well-being acknowledges that cognitive development and socio-emotional factors are intertwined and jointly contribute to individuals' overall mathematical competence (MC) which is integral to daily life.

This project addresses the critical challenge of improving mathematical competence for at-risk students, including low responders to current behavioural interventions in schools (Jamaludin et al, 2023), by leveraging digital gaming technology. Mathematics competency is vital for academic success and future career prospects, but many at-risk learners struggle over time, leading to negative cognitive and emotional outcomes. The project aims to develop a novel approach by identifying digital biomarkers within game-based learning environments that indicate enhanced mathematics well-being, encompassing cognitive and emotional aspects. The success of this project will contribute new knowledge by establishing a deeper understanding of how game-based interventions can positively impact at-risk learners' cognitive performance and emotional well-being. 

Team members:

Lead Principal Investigator: Asst Prof Azilawati Jamaludin
Co-PI: Dr Zhu Ying
 
Collaborator: Dr Tan Aik Lim

Mindful High-Intensity Interval Training Sessions (MINDFUL HIITS) is a Ministry of Education (MOE)-Science of Learning (SoL) research initiative that aims to elucidate the acute and long-term mechanisms underlying the combined effects of physical activity and mindfulness on student wellbeing, emotion regulation, and learning. By integrating neuroimaging and wearable physiological data, the study captures real-time indicators of arousal and stress during classroom learning, linking these markers to student wellbeing and academic achievement. Preliminary findings suggest that self-regulated learning (SRL)—a key factor in both wellbeing and performance—can be enhanced through targeted interventions, especially since self-evaluation emerged as the weakest SRL competency among Secondary 1 and 2 students. This points to the need for more explicit instruction on how students can reflect on and appraise their own learning efforts. Moreover, wearable data reveal fluctuations in student arousal underscores how stress impacts classroom learning, highlighting the importance of equipping students with strategies to regulate their emotions and physiological states to optimize engagement and cognitive performance.

The project also proposes an intervention integrated into Physical Education (PE) that combines mindfulness with high-intensity interval training (HIIT) to strengthen student emotion regulation and wellbeing. Beyond its immediate physiological benefits, the acute effects of exercise—potentially lasting up to two hours—may influence subsequent classroom learning and engagement, suggesting that school timetables could be strategically designed to leverage the positive effects of physical activity while minimizing fatigue or overstimulation. Teacher surveys will examine educators’ attitudes, needs, and barriers toward incorporating such practices, while local teachers will receive professional mindfulness training to sustain implementation. Collectively, this research has strong policy and practice implications, offering evidence-based recommendations for PE lesson design, school scheduling, and teacher professional development. It also demonstrates how wearable data can serve as a powerful, objective tool for evaluating classroom interventions and pedagogical factors that shape student regulation—advancing a neuroscience-informed, holistic approach to education in Singapore.

Funding body: MOE

Lead PI: Dr. Jack Fogarty

Co-PIs: Assoc. Prof. Teo Wei Peng

Collaborators: Asst. Prof. Alicia Marie Goodwill, Prof. Chia Yong Hwa Michael, Dr. Khng Kiat Hui, Dr. Lim Ashworth Shi Jie, Nikki (IMH)

As Singapore faces the dual challenges of an ageing workforce and rapid technological disruption driven by artificial intelligence and automation, the need for an adaptable, lifelong-learning population has never been more pressing. Adult learners—who often juggle work, family, and education—struggle with fatigue, time constraints, and motivational barriers that limit learning effectiveness. To address these challenges, the Physically Active Learning (PAL) project pioneers a transformative approach that embeds low-intensity physical activity into classroom teaching for adult learners. Drawing upon the principles of embodied cognition, PAL integrates purposeful movement before, during, or after instruction to improve attention, engagement, memory, and critical thinking. Adapted from the internationally recognized TransformUs® program, this locally contextualized intervention will be trialed across Singapore’s institutes of higher learning (IHLs) through a collaboration between NIE’s Science of Learning in Education Centre (SoLEC), the Singapore University of Social Sciences (SUSS), and Deakin University. Using neuroscientific and behavioural measures such as working memory, attention, and interbrain synchrony, the study will investigate how physical movement enhances not only learning performance but also the neurobiological mechanisms that underpin learning itself.

Beyond its scientific contributions, this project carries far-reaching implications for policy and educational practice. By integrating PAL pedagogies into adult education, the initiative aligns closely with Singapore’s Continuing Education and Training (CET) Masterplan and its goal to foster lifelong learning and workforce adaptability. The project’s findings could inform curriculum design, instructional planning, and teacher training in IHLs, supporting policies that promote active, brain-based learning environments for adults. Moreover, it highlights a scalable, evidence-based approach to enhancing wellbeing, cognitive resilience, and collaborative learning among adult learners, ensuring that Singapore’s workforce remains agile, innovative, and future-ready. Ultimately, PAL exemplifies how research at NIE and its partners can bridge neuroscience, pedagogy, and national manpower priorities—transforming how adults learn, think, and thrive in an era of constant change.

Funding Body: MOE SoL

Lead PI: Assoc. Prof. Teo Wei Peng

Co-PIs: Prof. David Hung Wei Loong, Asst. Prof. Azilawati Jamaludin, Dr. Stefanie Chye, Dr. Ho Yan Ying

International Collaborators: Assoc. Prof. Natalie Lander, Dr. Ana Marie Contardo Ayala, Prof. Jo Salmon

The EmoRoom project presents a research initiative that extends the exploration of learning emotions—particularly boredom—using multimodal data and visual analytics. Building upon earlier work in automated boredom detection using Electroencephalography (EEG), Electrocardiography (ECG), Galvanic Skin Response (GSR), and eye tracking data, this project advances towards a more classroom-relevant and scalable application. Emotions play a critical role in cognitive development and learning engagement, EmoRoom seeks to create an interactive visual analytics platform capable of unveiling student emotions from classroom video data. By integrating emotion recognition algorithms with intuitive visual interfaces, the system allows teachers to monitor and interpret students’ emotional states during lessons, supporting reflection on teaching strategies and class engagement. This approach addresses the longstanding challenge of teachers’ limited ability to accurately perceive and respond to subtle emotional cues in real time, especially when managing multiple students simultaneously

EmoRoom holds strong potential to inform teacher professional development, classroom design, and emotion-aware pedagogy in current educational practices. The platform’s scalability means educators and researchers can analyze classroom emotions across diverse contexts, both locally and internationally. Its offline functionality also enables users without technical backgrounds to explore classroom emotion data post-lesson, offering new possibilities for data-informed reflection and adaptive teaching. As an extension of the boredom detection study, which identified eye gaze as an optimal modality for emotion recognition and demonstrated how multimodal fusion enhances detection accuracy, EmoRoom exemplifies a translational effort to bring AI-driven emotion analytics into practical school use. By enabling teachers to detect, visualize, and interpret emotional engagement patterns, the project not only strengthens social-emotional learning (SEL) practices but also contributes to the broader goal of enhancing student wellbeing, reducing disengagement, and fostering emotionally intelligent learning environments within Singapore’s education system.

Funding Body: ERFP

Lead PI: Dr. Yuvaraj Rajamanickam

Team members: Dr. Jack Fogarty, Dr. Jun Song David Huang, Mr. Wong Teck Kiong (MOE), Mr. Tan Hsien Ming Samuel (MOE)

This project aims to synthesise global evidence on science of learning interventions that support students in literacy, numeracy, and well-being, particularly those from disadvantaged backgrounds or with special educational needs, across the Primary to Secondary education spectrum.

Using the PRISMA framework, we will conduct a systematic literature search to identify and screen eligible studies. Based on the volume and quality of available research, we will prioritize an umbrella review approach—focusing on existing meta-analyses, syntheses, and reviews. Where necessary, scoping reviews will be considered to ensure comprehensive coverage.

Our goal is to:

  • Identify effective, evidence-based interventions for each topic
  • Consolidate advancements and uncover gaps in current research and practice
  • Critically assess the implications of findings for educational equity and inclusion
  • Provide actionable insights to inform strategic initiatives and guide the national research agenda on Human Health Potential (HHP)

These evidence-based syntheses will serve as a foundation for reshaping educational practices, informing policy decisions, and driving strategic innovations that promote learning and holistic development for all students.

Funding body: SRF

Lead PI: Dr Astrid Schmied

Co-PIs: Dr Teo Chew Lee, Dr Wu Chiao Yi

Executive functions (EFs) are a set of cognitive processes that support goal-directed behaviours. They are associated with multiple life outcomes, including education, health, social functioning and emotional well-being (Fuhs et al. 2014; Moffitt et al., 2012; Stawski et al., 2010). Given the significance of EFs for our overall well-being, it is critical to examine the factors that may contribute to their healthy development. Physical activity, particularly those in the moderate- to high- intensity categories have been found to be beneficial to cognitive and brain functioning. The salutary effects of physical activity have also been reported on EFs across several studies. However, the qualitative characteristics of physical activity that are pivotal for bringing about the positive outcomes on EFs are not clear (Pesce et al. 2012). For instance, in a recent review, it was suggested that physical activity in the context of sports might carry more benefits than physical activity that is ‘plain’, or one that is repetitive and with minimal cognitive demands (Diamond & Ling, 2020). Although there is some suggestive evidence to support this hypothesis (Alesi et al., 2016; Ishihara et al., 2017), direct comparisons of sports-based physical activity with other less cognitive-engaging activities have not been made in studies examining EF. Insights into this association are particularly lacking in the adolescent age group, a period where significant growth in EF abilities is observed (Crone, 2009). Moreover, while there is some indication that those who have weaker EF abilities benefit more from EF intervention programmes, it is not known if this is the case with physical activity participation. This insight will allow for more targeted and tailored intervention approaches. The goal of this study is to examine the effects of cognitively-engaging physical activities on EFs and the associated brain activity in adolescents, and if such activities are more beneficial in adolescents with weaker EF abilities. A greater understanding on this topic would not only allow for better planning of physical activity curriculum in schools but also provide insights on interventions that can be effectively targeted to improve EFs in students, especially those with weak EFs.

Research Questions

(1) Do sports-based physical activities (e.g., volleyball, basketball) confer greater beneficial effects on EFs (Working memory, Inhibitory ability, and cognitive flexibility) than plain, repetitive aerobic physical activities (e.g., running, jump rope) that are less cognitively engaging?

(2) Are sports-based physical activity interventions associated with greater enhancement in brain activation patterns associated with EFs (i.e., ERPs that have been associated with WM, inhibition, and cognitive flexibility) than plain, repetitive physical activity interventions?  

(3) Are the effects of physical activities, particularly sports-based physical activities, on EF-related behavioural performance (i.e., accuracy, response time) and brain functioning (ERPs associated with EFs) more pronounced in adolescents with poorer EFs?

Impact Statement

The findings from this study will provide insights on the association between physical activity and EFs in Singaporean adolescents. Particularly, it can inform if specific types of physical activities (i.e., sports) are more beneficial for EFs. This understanding can be utilised in curriculum planning (physical education lessons) and more crucially, in designing effective interventions to foster EFs in adolescents.

PI: Dr. Aishah Abdul Rahman

Co-PI: Assoc. Prof. Teo Wei-Peng

Collaborator: Joel Chia Peng Hwee