Ph.D. Student: Alfredo Zapata
Advisors: Cristóbal Romero, Manuel Emilio Prieto
Defended on: February 2013
Keywords: learning objects, group recommendation systems, collaborative web search, metadata, repository, meta-learning
This thesis proposes a collaborative methodology for searching, selecting and rating LOs in a group. We have implemented this methodology into a hybrid recommendation system called DELPHOS, which is a framework to assist users in the single/individual personalised search for learning objects in repositories. We have extended DELPHOS with new functionalities, including the creation and management of groups of users, the realisation of collaborative activities, and the recommendation of the most interesting LOs to these groups. We also propose a meta-learning approach in order to help the mediator of a group to select the best rating aggregation method depending on the rating of previous similar groups. For one thing, the mediator is free to use any of the available aggregation strategies to automatically obtain the LO ratings from a group of users, without needing to use the traditional democratic in-person or online discussion to obtain a consensus from all the group members about each LO. But also, the mediator can directly use the best aggregation strategy recommended for a group based on its characteristics. In this way, the traditional time-consuming consensus-taking among users can be avoided by using an automatic method based on meta-learning and voting aggregation strategies.
PUBLICATIONS ASSOCIATED WITH THIS THESIS
- A. Zapata, V.H. Menéndez, M.E. Prieto and C. Romero. A framework for recommendation in learning object repositories: An example of application in civil engineering. Advances in Engineering Software, vol. 56, pp. 1-14. 2013.
- A. Zapata, V.H. Menéndez, M.E. Prieto and C. Romero. Using Data Mining in a Recommender System to Search for Learning Objects in Repositories. EDM 2011, pp. 321-322. 2011.