TY - JOUR AU - AB - TrueLearn: A Family of Bayesian Algorithms to Match Lifelong Learners to Open Educational Resources Sahan Bulathwela, Mar´ ıa Per ´ ez-Ortiz, Emine Yilmaz and John Shawe-Taylor Department of Computer Science, University College London Gower Street, London WC1E 6BT, UK fm.bulathwela, maria.perez, emine.yilmaz, j.shawe-taylorg@ucl.ac.uk Abstract educational materials, assisting learners on their personal learning pathway to achieve impactful learning outcomes. The recent advances in computer-assisted learning systems Personalised learning systems usually consist of two com- and the availability of open educational resources today promise a pathway to providing cost-efficient high-quality ponents (Lan, Studer, and Baraniuk 2014): (i) learning ana- education to large masses of learners. One of the most am- lytics, that capture the dynamic learner’s knowledge state bitious use cases of computer-assisted learning is to build a and (ii) content analytics, that extract characteristics of the lifelong learning recommendation system. Unlike short-term learning resource, such as knowledge components covered courses, lifelong learning presents unique challenges, requir- and resource quality/difficulty. In the context of learning an- ing sophisticated recommendation models that account for alytics, the assessment and learning science communities a wide range of factors such as background knowledge of aim to assess learner’s knowledge at a specific time point learners TI - TrueLearn: A Family of Bayesian Algorithms to Match Lifelong Learners to Open Educational Resources JF - Proceedings of the AAAI Conference on Artificial Intelligence DO - 10.1609/aaai.v34i01.5395 DA - 2020-04-03 UR - https://www.deepdyve.com/lp/unpaywall/truelearn-a-family-of-bayesian-algorithms-to-match-lifelong-learners-K9ubDzxOwV DP - DeepDyve ER -