RiPPLE: A Crowdsourced Adaptive Platform for Recommendation of Learning Activities

Abstract

This paper presents a platform called RiPPLE (Recommendation in Personalised Peer-Learning Environments) that recommends personalized learning activities to students based on their knowledge state from a pool of crowdsourced learning activities that are generated by educators and the students themselves. RiPPLE integrates insights from crowdsourcing, learning sciences, and adaptive learning, aiming to narrow the gap between these large bodies of research while providing a practical platform-based implementation that instructors can easily use in their courses. This paper provides a design overview of RiPPLE, which can be employed as a standalone tool or embedded into any learning management system (LMS) or online platform that supports the Learning Tools Interoperability (LTI) standard. The platform has been evaluated based on a pilot in an introductory course with 453 students at The University of Queensland. Initial results suggest that the use of the RiPPLE platform led to measurable learning gains and that students perceived the platform as beneficially supporting their learning. Notes for Practice• Adaptive learning systems (ALSs) dynamically adjust the level or type of instruction based on individual student abilities or preferences to provide a customized learning experience.• However, ALSs require access to a large repository of learning resources, which are commonly created by domain experts. This makes them expensive to develop and challenging to scale across different domains.• We introduce an ALS called RiPPLE that uses a crowdsourcing approach to engage students in creating, moderating, and evaluating learning resources. This both reduces the cost of content generation and has the potential to foster higher-order learning across many domains.• Initial results suggest that using RiPPLE may lead to measurable learning gains and that students perceived the platform as beneficially supporting their learning.

Charting the Design and Analytics Agenda of Learnersourcing Systems

“…A full description of RiPPLE is provided in [34]. Here, we provide a brief description based on the features of RiPPLE that are relevant to the context of this paper.…”

“…The literature suggests that the use of explainable AI (XIA) [61] is not always wanted or necessary [11]. However, the use of machine learning algorithms with black-box outcomes seems to be particularly inadequate for educational settings where educators strive to provide extensive feedback to enable learners to develop their own Much of the existing work on the need for open and XIA models in education has been conducted in the field of open learner models [9] where models are often opened through visualisations, as an important means of supporting learning through various systems such as learning analytics dashboards [10,54], intelligent tutoring systems [53], educational recommender systems [3], and adaptive learning platforms [34] (please see Section 3.3 for further discussion on use of explainable AI in education). In terms of learnersourcing systems, the problem of assessing quality of learnersourced contributions has been referred to or studied in previous work [19,25,47,63]; however the focus has generally been on maximising accuracy rather than explainability.…”

“…In contrast, educational tools have the general intention of improving learning which is more associated with high-quality active engagement rather than purposeless highquantity engagement. In the context of learnersourcing, past studies have referred to incentivising students to contribute as one of the important learnersoucing challenges that need to be addressed [28,34,66]. So how can learnersourcing systems be designed to encourage a large portion of the student population to contribute high-quality learnersourcing activities?…”

“…Previous studies have demonstrated examples of how learnersourcing can be used towards facilitating a learner-centred approach based on the aforementioned three points. Examples of employing learnersourcing to engage learners in higher-order learning tasks includes enabling students to create and evaluate knowledge components [47], multiple-choice questions [17,34], personalised hints [25], summaries of steps in how-to videos [64], explanations for peer instruction [7], solutions to open-ended questions [63], explanations for programming misconceptions [26], and comparing and contrasting pairs of similar learning artefacts [19]. Learnersourcing is also commonly used to support the delivery of feedback using peer assessment and grading systems (e.g., [52,67]), which have been demonstrated to help learners develop evaluative judgement, the capacity to make accurate evaluations about the quality of their work and that of others [33,56].…”

Repositioning students as co-creators of curriculum for online learning resources

“…Unique to the RiPPLE platform is the ability to allow for students and staff to be the joint co-creators of any given subject (Khosravi et al, 2019). Student and staff co-creation can be defined as a process where student and staff resources (e.g., ideas, feedback, platforms) interact to support improved student learning and/or experiences (Dollinger et al, 2018).…”