SDG 4: Quality Education
2. Project Details
Company or Institution
Data Scientist Network Foundation (Data Science Nigeria)
DSN EdTech AI Adaptive Learning Engine
General description of the AI solution
DSN EdTech is an AI-enabled adaptive learning solution that delivers personalized learning through a mix of audio classes and interactive SMS to bridge educational gaps for learners from low-income households who have no access to the internet or internet-ready devices.
The product video can be seen at https://www.youtube.com/watch?v=6CHhZdU3KSQ
The Adaptive learning engine platform enable students with featurephones to learn through two-way interactive classes delivered as summaries, short definitions, quizzes and revisions via SMS. In addition, for learners with limited internet access, long-format learning is delivered interactively via WhatsApp chatbot, Telegram chatbot, and localized low-bandwidth website in form of additional text, audio, and low-bit micro-class videos.
The product is guided by a back-end adaptive knowledge management engine that uses predictive analytics and a recommendation engine to deliver customized learning that addresses the unique needs of each learner, with or without the internet.
The AI Adaptive learning personalizes the learning experience as each learner can learn at their pace. Its pedagogy is based on student-centered learning where learning focuses on the distinct learning needs, interests, aspirations, or cultural backgrounds of each student. Such learning is customized per student based on their preferred learning style, competence, path, and context.
The Adaptive learning engine studies and detects the learning patterns of each child based on real-time quizzes, revisions, and intervention responses. All the students might be learning the same topic, but they will follow a unique path to master the concept. If a learner masters the concept faster, a more advanced topic is shared with an evaluation quiz.
However, if a learner fails to answer the quiz correctly, simpler examples and definitions to explain the concept better (a solution to the missed questions) are shared with the student, then new quizzes are given with more clarification to help the learner master the concept better.
Data Scientist Network Foundation (Data Science Nigeria)
Excellence and Scientific Quality: Please detail the improvements made by the nominee or the nominees’ team or yourself if your applying for the award, and why they have been a success.
DSN EdTech AI Adaptive Learning Engine Content uses recommendation engine and pattern recognition to curate, store, deliver and track individual students’ performance.
The AI Adaptive learning algorithm has been designed to study and detect each child’s learning patterns based on real-time quizzes, revisions, and intervention responses to the student.
The AI-enabled adaptive learning has also been programmed with questions on all the subjects and for each level. Each question is categorized in two ways for the students. If students get the question correctly, they move to more advanced questions to better understand the topic. If a learner fails to answer the quiz correctly, the AI algorithm has been designed to automatically send simpler examples and recommendations by fetching links to related topic content from our online radio content to enable the learner to understand the basics of the topic. The DSN EdTech AI Adaptive Learning Engine algorithm has also been trained to merge these responses with the missed questions’ solution and share it with the student.
When students completely master all the recommended content from our AI enable responses, they reply with (next), and our AI Algorithm will send new quizzes that are simpler to the student with more clarification to help the learner gain advanced knowledge of the topic.
Scaling of impact to SDGs: Please detail how many citizens/communities and/or researchers/businesses this has had or can have a positive impact on, including particular groups where applicable and to what extent.
There are over 40 million students in Nigeria, and another 10.5 million out-of-school children. With a core focus on SDG 4 (Quality Education), the DSN EdTech AI Adaptive Learning Engine project has helped learners from low-income households to access quality educational content, leading to a significant improvement in their academic performance and cognitive intelligence using our personalized learning model.
Over the last 9 months, Mastercard Foundation has supported our foundation in the deployment of this adaptive learning solution to support the learning of over 1.04 million students. The bespoke interactive learning platform (short USSD and SMS), version of the platform launched under the Learn at Home brand identity has supported students in the 37 states of Nigeria. An independent research on learners’ post-engagement research showed 97% satisfaction rate with significant evidence of learning progress across key outcome indicators.
Our AI Adaptive learning solution has the potential to reach an estimated 5 million learners in Nigeria and 3 million across other sub-Saharan African, over the next 3 years, as we continue to scale the bespoke solution, with more localized contents, created with improved text-to-speech learning localization and interactive gamification capabilities, for an immersive, and personalized learning experience.
Scaling of AI solution: Please detail what proof of concept or implementations can you show now in terms of its efficacy and how the solution can be scaled to provide a global impact ad how realistic that scaling is.
Our Adaptive learning model has continually been trained with a large dataset of materials in local languages. We are scaling the solution to become extremely useful in helping to deliver learning in local languages. Leveraging these materials can lead to better contextualization of the learning contents and ultimately allow young learners in close-out communities to gain access to well-curated and localized learning content.
Ethical aspect: Please detail the way the solution addresses any of the main ethical aspects, including trustworthiness, bias, gender issues, etc.
From an ethical perspective, all the data privacy laws in Nigeria and particularly the 2019 Nigerian Data Protection Regulation (NDPR) which is the principal data privacy regulation in Nigeria, have been complied with to ensure that the personal data and identity of every child is protected. The algorithm uses anonymized and de-identified data to profile and build a recommendation engine, with optimal regard for the privacy of each learner.
Our solution democratizes access to global standard educational content and provides an equal opportunity for young learners to access this content through our zero-rated audio learning platforms and offline distribution channels such as local content-copying centers and distribution kiosks.
Furthermore, to ensure greater inclusion, we developed localized content, created and delivered in local Nigerian languages, across critical subjects. This proved to be hugely valuable to learners who grew up with their local dialects as their first language, as concepts in these subjects were explained in their local dialect, engendering greater engagement, interest, and understanding of these subjects.