Page 15

www.rsisinternational.org

ILEIID 2025 | International Journal of Research and Innovation in Social Science (IJRISS)

ISSN: 2454-6186 | DOI: 10.47772/IJRISS

Special Issue | Volume IX Issue XXII October 2025

Transforming Teaching and Learning through LIFT: A Structured

Dashboard for Education 5.0

Nur ‘Amirah Mhd Noh

, Ahmad Amru Mohamad Zaid

, Rabeah Md Zin

Faculty of Built Environment, Universiti Teknologi MARA

School of Computing and Artificial Intelligence, Malaysia University of Science and Technology

Department of Civil Engineering, Polytechnic Sultan Azlan Shah, Ministry of Higher Education

*Corresponding author

DOI: https://dx.doi.org/10.47772/IJRISS.2025.922ILEIID003

Received: 23 September 2025; Accepted: 30 September 2025; Published: 22 October 2025

ABSTRACT

The rapid advancement of digital technologies calls for innovative approaches in language and education that

are inclusive, adaptive, and future-ready. This project introduces LIFT (Learning Input Feedback

Transformation), a structured dashboard designed to elevate teaching and learning by guiding students from

initial input to meaningful outcomes through continuous feedback. The core innovation of LIFT lies in its

integration of AI with multilingual and assistive tools, ensuring that learning is both personalized and

inclusive, particularly for marginalized and differently abled students. The dashboard is structured into four

interconnected components. Learner Engagement (Input Layer) collects data on learning styles, language

proficiency, progress, and accessibility needs using tools such as voice-to-text, real-time translation, and sign

language recognition. AI Analytics (Processing Layer) applies adaptive algorithms and natural language

processing to tailor content, forecast learner performance, and deliver timely support. Teaching and Learning

Enhancement generates individualized lesson plans, interactive learning materials, automated grading, and AI-

assisted coaching to improve engagement and outcomes. Finally, Feedback and Continuous Improvement

ensures personalized feedback for learners and provides educators with actionable insights for refinement. By

blending educational creativity with technological inclusion, LIFT ensures that AI complements rather than

replaces educators. Its adaptive, multilingual design supports Education 5.0 and advances Sustainable

Development Goal 4 (Quality Education). Ultimately, LIFT redefines knowledge delivery and accessibility,

making education a powerful enabler of empowerment, equity, and innovation.

Keywords: Digital technologies, teaching and learning, language, education

INTRODUCTION

Education is moving from teacher-centred knowledge transmission to learner-centred, data-informed

ecosystems. This shift is driven by advances in artificial intelligence in education, which has grown rapidly

across areas such as personalization, assessment, tutoring, and analytics (Wang et al., 2024). Systematic

reviews show that AI-powered adaptive learning can improve engagement and outcomes but also risk

deepening inequalities if inclusivity is not addressed (Bond et al., 2024). In parallel, the vision of Education

5.0 emphasises human-centred learning ecosystems that balance technological innovation with equity, ethics,

and social sustainability (Shahidi Hamedani et al., 2024). Evidence from universal design of learning and

learning analytics reinforces the value of designing proactively for learner variability and transforming

learning traces into actionable insights (Almeqdad et al., 2023; Roski et al., 2024). Against this backdrop, LIFT

emerges as a structured pipeline that brings together learner profiling, AI analytics, multilingual and assistive

supports, teaching enhancements, and continuous feedback into a single end product: a dashboard that can be

accessed by teachers, parents, and students alike.

Page 16

www.rsisinternational.org

ILEIID 2025 | International Journal of Research and Innovation in Social Science (IJRISS)

ISSN: 2454-6186 | DOI: 10.47772/IJRISS

Special Issue | Volume IX Issue XXII October 2025

Problem Statement

While digital learning platforms are more widespread than ever, they continue to fall short in addressing equity

and inclusion. Learners from multilingual, rural, or low-resource backgrounds, as well as those with

disabilities, often encounter systemic barriers. Monolingual interfaces and limited translation accuracy prevent

learners from fully engaging with content, while the lack of integrated assistive solutions such as sign-

language recognition or captioning reduces accessibility for differently abled students (Papastratis et al., 2021;

Rastgoo et al., 2021). Even where such solutions exist, they are typically fragmented add-ons rather than being

seamlessly integrated into learning platforms (Alaghband & Sadeghi, 2023). At the same time, teachers

face data overload, activity logs, quiz scores, and engagement metrics are often scattered across multiple

systems, making it difficult to synthesize these into clear, actionable insights (Roski et al., 2024). Without

structured feedback loops, educators cannot adapt instruction effectively, while learners and parents remain

disconnected from the learning process. These gaps underline the urgent need for an integrated framework like

LIFT that combines assistive tools, AI-driven analytics, and continuous feedback into a shared dashboard,

thereby creating transparency, personalization, and collaborative accountability across the learning community.

Objectives

The objectives of LIFT are twofold.

1. To provide personalized learning pathways tailored to the diverse needs of learners, particularly with

respect to language proficiency and accessibility.

2. To integrate multilingual and assistive technologies such as speech-to-text, real-time translation, and

sign-language recognition to ensure equitable access for all students.

Product Description

The end product is a web-based dashboard designed primarily for teachers to plan, monitor, intervene, and

reflect, while parents and students access curated read-only views to track goals, progress, and feedback. LIFT

dashboard designed based on the curated term LIFT which the first element L stands for the Learner

Engagement referring to the Input Layer. The dashboard ingests learning style indicators, language proficiency,

accommodations, and ongoing activity via connectors to the Learning Management System (LMS) and content

tools. Accessibility inputs can include voice-to-text, real-time translation, and sign-language

recognition capture (Papastratis et al., 2021; Rastgoo et al., 2021). Student or parent views show current goals

and accessible settings, while teachers can batch-review profiles for a class and spot unmet needs (Matre et al.,

2024).

The second element is AI Analytics referring to he Processing Layer. The platform applies adaptive algorithms

and NLP to personalize content sequencing, predict risk, and surface explainable recommendations aligned

with learning design. Where appropriate, automated assessment of short-answer or essay-type responses

expedites timely formative feedback (Gao et al., 2024). The teacher dashboard emphasizes human-in-the-

loop control in which all predictions show uncertainty, provenance, and suggested next actions (Bond et al.,

2024; Wiley et al., 2024).

Teaching & Learning Enhancement is the third element. From the dashboard, teachers generate individualized

lesson pathways, scaffold interactive materials, and trigger real-time coaching (e.g., hints, exemplars,

multilingual glossaries). When teachers enable automated scoring or feedback for drafts, the system

returns specific, criteria-referenced comments while preserving teacher oversight (Shi et al., 2024). Parents and

students see progress snapshots and next-step suggestions written in plain language.

Finally, is the F referring to the Feedback & Continuous Improvement. The dashboard aggregates formative

feedback for learners and actionable insights for teachers (what to reteach, who to check-in with, which

accessibility supports are under-utilized). A reflection panel summarizes what worked for different subgroups,

Page 17

www.rsisinternational.org

ILEIID 2025 | International Journal of Research and Innovation in Social Science (IJRISS)

ISSN: 2454-6186 | DOI: 10.47772/IJRISS

Special Issue | Volume IX Issue XXII October 2025

supporting iterative course improvement and school-level equity monitoring (Alfredo et al., 2024; Wiley et al.,

2024).

Figure 1 Structured dashboard of LIFT

This figure presents a sequence that is embedded in the teacher dashboard, parents and students’ views expose

a simplified version (goals, progress, feedback) without predictive controls (Wiley et al., 2024; Alfredo et al.,

2024).

METHODOLOGY

This project adopt a human-centred, design-based research approach to co-design with teachers, students, and

parents, iterating toward a minimally-viable dashboard that is pedagogically useful and contextually scalable

(Wiley et al., 2024; Alfredo et al., 2024). Recent studies show that participatory co-design is widely used in

developing educational dashboards to build trust, usability, and alignment with classroom practice. For

example, Herodotou et al. (2025) and Alfredo et al. (2024) demonstrated that co-design with teachers and

learners improves dashboard relevance, while Mohseni et al. (2023) and Kaliisa et al. (2023) showed how

collaborative workshops enhance teacher adoption. Likewise, Pozdniakov et al. (2021, 2022) and Dey et al.

(2022) highlighted that iterative prototyping ensures dashboards respond to authentic pedagogical needs.

However, these studies often remain narrow in focus, addressing only specific contexts such as teacher

analytics or student writing processes. The novelty of LIFT is that it brings everything together in one

structured dashboard, while it not only tracks learning progress but also integrates multilingual support,

assistive tools for differently abled learners, AI-driven insights, and continuous feedback. In simpler terms,

while earlier dashboards focused mainly on usability or single features such as grading or discussion tracking,

LIFT is designed for fairness and inclusion, accessible to everyone, and partnership between humans and AI.

This makes it a more powerful and future-ready tool that directly supports the goals of Education 5.0 and SDG

The participatory co-design methodology directly supports the project’s objectives by ensuring that each

design decision is rooted in authentic classroom needs. First, by engaging teachers, students, and parents in

workshops and contextual inquiries, the dashboard is structured to create personal learning paths that reflect

diverse student needs, abilities, and accessibility requirements. Second, the inclusion of multilingual and

assistive technologies such as voice-to-text, real-time translation, and sign-language recognition is embedded

from the earliest prototype sprints, fulfilling the objective of using inclusive tools so that no learner is left

behind. Third, the co-design process prioritizes teacher input in identifying actionable “jobs to be done,”

Page 18

www.rsisinternational.org

ILEIID 2025 | International Journal of Research and Innovation in Social Science (IJRISS)

ISSN: 2454-6186 | DOI: 10.47772/IJRISS

Special Issue | Volume IX Issue XXII October 2025

allowing the dashboard to deliver smart insights that make teaching more effective and reduce workload, in

line with the objective. Finally, the iterative testing and mixed-methods evaluation phases ensure the system

is aligned with Education 5.0 and UN SDG 4 by promoting inclusivity, equity, and lifelong learning

opportunities. In this way, the methodology is not only technical but also pedagogically grounded, ensuring

that the LIFT dashboard advances both innovation and educational transformation.

Potential Findings and Commercialisation

We anticipate that LIFT will yield to improve formative feedback timeliness and higher student participation,

consistent with evidence that dashboards can support engagement when human-centred and aligned to learning

design (Wiley et al., 2024; Alfredo et al., 2024). In addition, LIFT yield to reduce teacher time-on-

marking through selective use of automated assessment and feedback, with teacher control to calibrate and

override (Gao et al., 2024; Shi et al., 2024). Furthermore, LIFT is measurable inclusion gains (e.g., more

consistent use of captions, translation, or sign-language support) relative to baseline (Papastratis et al., 2021).

For commercialization, the product is scalable as a cloud service, integrable with mainstream LMSs and viable

as a business-to-business (B2B) offering for schools, universities, and training providers. The assistive-tech

and EdTech markets, combined with policy attention to accessibility and SDG 4, create strong demand and

partnership opportunities with ministries, NGOs, and industry (Nedungadi et al., 2024).

Overcoming Barriers and Building Responsible AI in Education

To address the first issue with practical barriers, a lot of schools, particularly in rural or low-resource areas,

struggle with things like poor internet access and not enough devices, which makes it tough to use AI tools

fairly. Some ideas to consider are rolling things out in phases, adding features that work offline, and teaming

up with ministries or NGOs to help with hardware support. It's super important to focus on teacher training and

leadership support because teachers really need to feel confident and have a solid backing when they're trying

out new tech. Having clear rules about data protection and accessibility standards is super important for

making sure everything is fair and works well for everyone. These updates match what we've seen in research

about digital inequality, the struggles in rural education, and how ready teachers are to use AI (Wang et al.,

2024)

Some parts of the original text were too technical, so they have been rewritten in simpler language. To make

the ideas more concrete, the project added two short classroom scenarios: one set in a rural multilingual class

where students benefit from real-time translation and speech-to-text, and another in an inclusive urban class

where captioning and sign-language recognition help differently abled learners. These examples show clearly

how LIFT can be used in practice, while also keeping teachers in control of the learning process. This approach

aligns with co-design research that shows how teacher involvement and real classroom examples make

educational technology more relevant and effective (Sibley et al., 2024).

The third area that need to work on is governance, ethics, and data security. The project has a governance plan

that features regular bias checks, a human-in-the-loop review for AI suggestions, and decision logs to keep

things transparent about how the system works. There's a bigger focus on keeping data safe by suggesting

things like anonymising it, storing it securely, and collecting only what you really need. It's super important to

protect kids' rights and privacy in schools. These updates match up with the latest stuff on responsible AI

governance and ethics in education (Papagiannidis et al., 2025).

Looking ahead, the paper points out plans to check out how LIFT-enabled classrooms stack up against

traditional ones by looking at teacher workload, student outcomes, and inclusivity indicators like how often

accessibility tools are used. Additional steps include testing school-level governance measures to ensure long-

term fairness, ethical use, and sustainability. These directions build upon prior studies of dashboards and

responsible AI implementation in education (Papagiannidis et al., 2025).

Page 19

www.rsisinternational.org

ILEIID 2025 | International Journal of Research and Innovation in Social Science (IJRISS)

ISSN: 2454-6186 | DOI: 10.47772/IJRISS

Special Issue | Volume IX Issue XXII October 2025

Novelty and Recommendations

LIFT’s novelty lies in unifying AI analytics, adaptive algorithms, and multilingual assistive tools into a

single teacher-centred dashboard explicitly designed for human-AI collaboration. Unlike tool-silos, LIFT

couples’ predictive insights with explainable next actions and accessibility-aware content generation, then

closes the loop with feedback analytics to refine both teaching and system prompts (Bond et al., 2024; Gao et

al., 2024). We recommend districts pilot LIFT in co-design partnerships, mandate accessibility-

first configurations (WCAG 2.2 AA), and adopt governance for model monitoring, bias audits, and data

minimization. Future studies should compare teacher workload, learner outcomes, and equity indicators across

LIFT-enabled vs. status-quo courses over a semester and examine long-term impacts aligned with Education

5.0 and SDG 4 (Shahidi Hamedani et al., 2024; Nedungadi et al., 2024).

ACKNOWLEDGEMENTS

The authors gratefully acknowledge the contributions of the project members and the recognition to those

involved in this project.

REFERENCES

1. Alaghband, M., & Sadeghi, S. (2023). A survey on sign language literature. Discover Artificial Intelligence,

3(1), 18. https://doi.org/10.1016/j.mlwa.2023.100504

2. Alfredo, R., Echeverria, V., Jin, Y., Yan, L., Swiecki, Z., Gašević, D., & Martinez-Maldonado, R. (2024).

Designing a human-centred learning analytics dashboard in-use. Journal of Learning Analytics, 11(3), 1–

26. https://doi.org/10.18608/jla.2024.8487

3. Almeqdad, Q. I., et al. (2023). The effectiveness of Universal Design for Learning: A systematic review and

meta-analysis. Cogent Education, 10(1), 2218191. https://doi.org/10.1080/2331186X.2023.2218191

4. Bond, M., Holford, M., Aden-Ulley, J., Nerantzi, C., & Rosli, N. A. (2024). A meta-systematic review of

artificial intelligence in higher education: A call for increased ethics, collaboration, and rigour. International

Journal of Educational Technology in Higher Education, 21, Article 25. https://doi.org/10.1186/s41239-023-

00436-z

5. Gao, R., Merzdorf, H. E., Anwar, S., Hipwell, M. C., & Srinivasa, A. R. (2024). Automatic assessment of

text-based responses in post-secondary education: A systematic review. Computers & Education: Artificial

Intelligence, 6, 100206. https://doi.org/10.1016/j.caeai.2024.100206

6. Herodotou, C., Cukurova, M., Rienties, B., Hlosta, M., & Boroowa, A. (2025). A participatory approach to

designing a student-facing dashboard for online and distance education. Journal of Learning Analytics,

12(1), 1–22. https://doi.org/10.18608/jla.2025.8481

7. Matre, M. E., Mjøs, J. A., & Høigaard, S. (2024). A scoping review on the use of speech-to-text technology

in secondary education for students with learning difficulties. Scandinavian Journal of Educational

Research. Advance online publication. http://dx.doi.org/10.1080/17483107.2022.2149865

8. Nedungadi, P., Tang, K.-Y., & Raman, R. (2024). The transformative power of generative artificial

intelligence for achieving the Sustainable Development Goal of Quality Education. Sustainability, 16(22),

9779. https://doi.org/10.3390/su16229779

9. Papastratis, I., Chatzikonstantinou, C., Dimou, A., & Daras, P. (2021). Artificial intelligence technologies

for sign language: A survey. Sensors, 21(17), 5843. https://doi.org/10.3390/s21175843

10. Papagiannidis, E., Mikalef, P., & Conboy, K. (2025). Responsible artificial intelligence governance: A

review and research framework. The Journal of Strategic Information Systems, 34(2), 101885.

https://doi.org/10.1016/j.jsis.2024.101885

11. Rastgoo, R., Kiani, K., & Escalera, S. (2021). A deep survey on sign language recognition. Expert Systems

with Applications, 183, 115657. https://doi.org/10.1016/j.eswa.2021.115657

12. Roski, M., Sebastian, R., Ewerth, R., Hoppe, A, & Nehring, A. (2024). Learning analytics and the Universal

Design for Learning (UDL): A clustering approach. Computers & Education, 214,

105028. https://doi.org/10.1016/j.compedu.2024.105028

Page 20

www.rsisinternational.org

ILEIID 2025 | International Journal of Research and Innovation in Social Science (IJRISS)

ISSN: 2454-6186 | DOI: 10.47772/IJRISS

Special Issue | Volume IX Issue XXII October 2025

13. Sibley, L., Broughton, D., & Stürmer, K. (2024). Feasibility of adaptive teaching with technology: A four-

year co-design project with teachers. Computers &

Education,214, 105028. https://doi.org/10.1016/j.compedu.2024.105028

14. Shi, Y., Luo, S., & Li, J. (2024). A systematic review of AI-based automated written feedback

research. ReCALL, 36(2), 194–212. https://doi.org/10.1017/S0958344023000265

15. Shahidi Hamedani, S., Aslam, S., Mundher Oraibi, B. A., Wah, Y. B., & Shahidi Hamedani, S. (2024).

Transitioning towards tomorrow’s workforce: Education 5.0 in the landscape of Society 5.0 : A systematic

literature review. Education Sciences, 14(10), 1041. https://doi.org/10.3390/educsci14101041

16. Wang, S., Chen, Y., Zhao, C., & Li, X. (2024). Artificial intelligence in education: A systematic literature

review. Expert Systems with Applications, 244, 124167. https://doi.org/10.1016/j.eswa.2024.124167

17. Wang, F., Ni, X., Zhang, M., & Zhang, J. (2024). Educational digital inequality: A meta-analysis of the

relationship between digital device use and academic performance in adolescents. Computers &

Education, 213, 105003. https://doi.org/10.1016/j.compedu.2024.105003

18. Wiley, K., Buckingham Shum, S., Echeverria, V., et al. (2024). A human-centred learning analytics

approach for developing contextually scalable K-12 teacher dashboards. British Journal of Educational

Technology, 55(3), 1061–1081. https://doi.org/10.1111/bjet.13383