Idir Benouaret

A simple yet effective interpretable bayesian personalized ranking for cognitive diagnosis

By Arthur Batel, Idir Benouaret, Joan Fruitet, Marc Plantevit, Céline Robardet

2024-10-10

In ECAI 2024 - 27th european conference on artificial intelligence

Abstract

In the field of education, the automatic assessment of student profiles has become a crucial objective, driven by the rapid expansion of online tutoring systems and computerized adaptive testing. These technologies aim to democratize education and enhance student assessment by providing detailed insights into student profiles, which are essential for accurately predicting the outcomes of exercises, such as solving various types of mathematical equations. We aim to develop a model capable of predicting responses to a large set of questions within the Multi-Target Prediction framework while ensuring that this model is explainable, allowing us to quantify student performance in specific knowledge areas. Existing cognitive diagnosis algorithms often struggle to meet the dual requirement of accurately predicting exercise outcomes and maintaining interpretability. To address this challenge, we propose an alternative to the complexity of current advanced machine learning models. Instead, we introduce a direct yet highly effective Bayesian Personalized Ranking algorithm, called CD-BPR, which incorporates interpretability as a core learning objective. Extensive experiments demonstrate that CD-BPR not only performs better in predicting exercise outcomes but also provides superior interpretability of estimated student profiles, thus fulfilling both key requirements.

Continue reading

Adaptive test recommendation for mastery learning

By Nassim Bouarour, Idir Benouaret, Cédric D’Ham, Sihem Amer-Yahia

2023-06-12

In Proceedings of the 2nd international workshop on data systems education: Bridging education practice with education research

Abstract

We tackle the problem of recommending tests to learners to achieve upskilling. Our work is grounded in two learning theories: mastery learning, an instructional strategy that guides learners by providing them tests of increasing difficulty, reviewing their test results, and iterating until they reach a level of mastery; Flow Theory, which identifies different test zones, frustration, learnable, flow and boredom zones, to determine the best k tests to recommend to a learner. We formalize the AdUp Problem and develop a multi-objective optimization solution that adapts the difficulty of recommended tests to the learner’s predicted performance, aptitude, and skill gap. We leverage existing models to simulate learner behavior and run experiments to demonstrate that our formalization is best to attain skill mastery. We discuss open research directions including the applicability of reinforcement learning and the recommendation of peers in collaborative projects.

Continue reading

Learning diversity attributes in multi-session recommendations

By Nassim Bouarour, Idir Benouaret, Sihem Amer-Yahia

2022-12-12

In 2022 IEEE international conference on big data (big data)

Abstract

Diversity in recommendation has been studied extensively. It has been shown that maximizing diversity subject to constrained relevance yields high user engagement over time. Existing work largely relies on setting some attributes that are used to craft an item similarity function and diversify results. In this paper, we examine the question of learning diversity attributes. That is particularly important when users receive recommendations over multiple sessions. We devise two main approaches to look for the best diversity attribute in each session: the first is a generalization of traditional diversity algorithms and the second is based on reinforcement learning. We implement both approaches and run extensive experiments on a semi-synthetic dataset. Our results demonstrate that learning diversity attributes yields a higher overall diversity than traditional diversity algorithms. We also find that training policies using reinforcement learning is more efficient in terms of response time, in particular for high dimensional data.

Continue reading

Search

Tags