A proactive strategy that fosters diversity The reactive strategy: combining long-term and short-term learning goals Personalized and diversity-aware recommendation strategies for educational resources Almudena Ruiz Iniesta, Mercedes Gómez Albarrán and Guillermo Jiménez Díaz Department of Software Engineering and Artificial Intelligence – Computer Science School – Complutense University of Madrid Acknowledgments Supported by: Spanish Ministry of Science and Education under grant TIN2009-13692-C03-03; and Complutense University of Madrid and BSCH under grant 921330-1079 for consolidated Research Groups. Collaborative strategy Case-based strategy Reactive strategy Proactive strategy Collaborative strategy Cascade Hybrid Recommender Personalization & Diversity Learning community opinion The development of electronic repositories with high number of educational resources has been intensified Recommender systems support users in pre-selecting information they may be interested in We propose a recommendation approach for repositories of LOs that adapts to the student learning profile Motivation Required knowledge Domain ontology Domain concepts Precedence property among the concepts Learning Objects Cascade Hybrid Recommender Retrieve LOs that cover same or similar concepts Filter LOs not ready to be explored Rank according to the LO Quality Retrieval step Ranking step Student query {if, for,…} Ranked list of recommended LOs Student profile The goals achieved in the learning process Mastery level achieved in each concept Preference repository Rating scores explicitly assigned by the students to each LO The profile that the student had when she rated the LO Diversity Select LOs from different partitions in the space of LOs First stage Reinforce Discover Recommender systems in the learning domain impose new challenges in the evaluation process More important to measure the impact of the recommender in the final user Goal-Questions Metrics method Analyzing the usability of the repository Analyzing students’ grades Analyzing the impact of different recommendation strategies Basili VR, Rombach HD. The TAME project: towards improvement-oriented software environments. Software Engineering, IEEE Transactions on. 1988;14(6):758-773 Open Issues Collaborative strategy Second stage Repeat until leaves are reached User-based nearest neighbour Neighbourhood formation candidates: students who rated the LOs proposed by the case-based recommender similarity between the target student profile and the profile that the neighbour had when she rated the LO Rating prediction and top-k selection Repository of LOs for Computer Programming