Personalized Education in the Artificial Intelligence Era: What to Expect Next

  title={Personalized Education in the Artificial Intelligence Era: What to Expect Next},
  author={Setareh Maghsudi and Andrew S. Lan and Jie Xu and Mihaela van der Schaar},
  journal={IEEE Signal Processing Magazine},
The objective of personalized learning is to design an effective knowledge acquisition track that matches the learner's strengths and bypasses his/her weaknesses to ultimately meet his/her desired goal. This concept emerged several years ago and is being adopted by a rapidly growing number of educational institutions around the globe. In recent years, the rise of artificial intelligence (AI) and machine learning (ML), together with advances in big data analysis, has introduced novel… 

Figures and Tables from this paper

Artificial Intelligence in Education: AIEd for Personalised Learning Pathways

Artificial intelligence is the driving force of change focusing on the needs and demands of the student. The research explores Artificial Intelligence in Education (AIEd) for building personalised

Classification and Analysis of College Students’ Skills Using Hybrid AI Models

A hybrid artificial intelligence (AI) system that fully automates the process of personalized training is proposed based on individual skills by taking into account the priority of personalized and fully customized learning systems.

Personalized Hybrid Education Framework Based on Neuroevolution Methodologies

  • Wenjing Yin
  • Computer Science
    Computational intelligence and neuroscience
  • 2022
A neuroevolution emerging technique that combines the searchability of evolutionary computation and the learning capability of a hybrid artificial neural networks method is proposed.


Artificial Intelligence (AI) is changing the way people live in society. New technologies powered by AI have been applied in different sectors of the economy and the educational context is no

Personalized assessment: Applying higher-order cognitive diagnosis models in secondary mathematics

Personalized assessment is an essential component in education. Although many cognitive diagnosis models (CDMs) have been developed for this purpose, few studies have applied them in secondary

Internet of Intelligence: A Survey on the Enabling Technologies, Applications, and Challenges

This paper investigates the evolution of networking paradigms and artificial intelligence (AI) by demonstrating that networking needs intelligence and intelligence needs networking, and presents the layered architecture to characterize the Internet of Intelligence systems and discusses the enabling technologies of each layer.



A Contextual Bandits Framework for Personalized Learning Action Selection

This work develops two algorithms for personalized learning action selection and experimentally validate one using a real-world educational dataset and demonstrates that the approach achieves superior or comparable performance as compared to existing algorithms in terms of maximizing the students’ immediate success.

Context-Aware Attentive Knowledge Tracing

Attentive knowledge tracing is proposed, which couples flexible attention-based neural network models with a series of novel, interpretable model components inspired by cognitive and psychometric models and exhibits excellent interpretability and thus has potential for automated feedback and personalization in real-world educational settings.

Personalized Course Sequence Recommendations

A forward-search backward-induction algorithm is developed that can optimally select course sequences to decrease the time required for a student to graduate and optimally recommend a course sequence that reduces the time to graduate while also increasing the overall GPA of the student.

Performance Factors Analysis - A New Alternative to Knowledge Tracing

This paper describes the work to modify an existing data mining model so that it can also be used to select practice adaptively, and compares this new adaptive datamining model (PFA, Performance Factors Analysis) with two versions of LFA and then compares PFA with standard KT.

QG-net: a data-driven question generation model for educational content

QG-Net, a recurrent neural network-based model specifically designed for automatically generating quiz questions from educational content such as textbooks, is introduced and outperforms state-of-the-art neuralNetwork-based and rules-based systems for question generation.

Deep Knowledge Tracing

The utility of using Recurrent Neural Networks to model student learning and the learned model can be used for intelligent curriculum design and allows straightforward interpretation and discovery of structure in student tasks are explored.

Learning materials recommendation using good learners’ ratings and content-based filtering

The proposed e-learning recommender system framework works on the idea of recommending learning materials with a similar content and indicating the quality of learning materials based on good learners’ ratings and performed better in terms of having a small rating deviation and a higher precision as compared to e- learning with a content-basedRecommender system.

Exploring Automated Question Answering Methods for Teaching Assistance

The use of automated question answering methods to power virtual TAs in online course discussion forums, which are heavily relied on during the COVID-19 pandemic as classes transition online, are explored.

Personalized Thread Recommendation for MOOC Discussion Forums

A probabilistic model for the process of learners posting on discussion forums, using point processes, that excels at thread recommendation, achieving significant improvement over a number of baselines, thus showing promise of being able to direct learners to threads that they are interested in more efficiently.

Contextual multi-armed bandit algorithms for personalized learning action selection

This paper proposes three new Bayesian policies to select personalized learning actions for students that each exhibits advantages over prior work, and experimentally validate them using real-world datasets.