| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 1.33 MB | Adobe PDF |
Authors
Advisor(s)
Abstract(s)
O aumento do nĆŗmero de recursos digitais disponĆveis dificulta a tarefa de pesquisa dos recursos mais relevantes, no sentido de se obter o que Ć© mais relevante. Assim sendo, um novo tipo de ferramentas, capaz de recomendar os recursos mais apropriados Ć s necessidades do utilizador, torna-se cada vez mais necessĆ”rio. O objetivo deste trabalho de I&D Ć© o de implementar um mĆ³dulo de recomendaĆ§Ć£o inteligente para plataformas de e-learning. As recomendaƧƵes baseiam-se, por um lado, no perfil do utilizador durante o processo de formaĆ§Ć£o e, por outro lado, nos pedidos efetuados pelo utilizador, atravĆ©s de pesquisas [Tavares, Faria e Martins, 2012].
O e-learning 3.0 Ć© um projeto QREN desenvolvido por um conjunto de organizaƧƵes e tem com objetivo principal implementar uma plataforma de e-learning. Este trabalho encontra-se inserido no projeto e-learning 3.0 e consiste no desenvolvimento de um mĆ³dulo de recomendaĆ§Ć£o inteligente (MRI). O MRI utiliza diferentes tĆ©cnicas de recomendaĆ§Ć£o jĆ” aplicadas noutros sistemas de recomendaĆ§Ć£o. Estas tĆ©cnicas sĆ£o utilizadas para criar um sistema de recomendaĆ§Ć£o hĆbrido direcionado para a plataforma de e-learning. Para representar a informaĆ§Ć£o relevante, sobre cada utilizador, foi construĆdo um modelo de utilizador. Toda a informaĆ§Ć£o necessĆ”ria para efetuar a recomendaĆ§Ć£o serĆ” representada no modelo do utilizador, sendo este modelo atualizado sempre que necessĆ”rio. Os dados existentes no modelo de utilizador serĆ£o utilizados para personalizar as recomendaƧƵes produzidas.
As recomendaƧƵes estĆ£o divididas em dois tipos, a formal e a nĆ£o formal. Na recomendaĆ§Ć£o formal o objetivo Ć© fazer sugestƵes relacionadas a um curso especĆfico. Na recomendaĆ§Ć£o nĆ£o-formal, o objetivo Ć© fazer sugestƵes mais abrangentes onde as recomendaƧƵes nĆ£o estĆ£o associadas a nenhum curso. O sistema proposto Ć© capaz de sugerir recursos de aprendizagem, com base no perfil do utilizador, atravĆ©s da combinaĆ§Ć£o de tĆ©cnicas de similaridade de palavras, um algoritmo de clustering e tĆ©cnicas de filtragem.
As more and more digital resources are available, finding the appropriate document becomes harder. Thus, a new kind of tools, able to recommend the more appropriated resources according the user needs, becomes even more necessary. The objective of this I&D work is to implement an intelligent recommendation module (MRI) for e-learning platforms. The recommendations are based on one hand, the performance of the user profile and on the other hand, the requests made by the user in the form of search queries [Tavares, Faria e Martins, 2012]. The e-learning 3.0 is a project developed by a group of organizations and has as primary objective the development of an e-learning platform. This work is inserted in the project e-learning 3.0 being responsible for the MRI. The MRI uses different techniques, which are already being used in recommendation systems, and apply those techniques to create a hybrid tutoring system for an e-learning platform. A user model was built to represent the relevant information about each user. All the information needed to do a recommendation is represented in that model, the model will be updated every time it is necessary. The data in the user model will be used to personalize the produced recommendations. The recommendations are divided into two types, the formal recommendation and the non-formal recommendation. In the formal recommendation the goal is to make suggestions related to a specific course. In the non-formal recommendation the purpose is to make suggestions that are not associated with any course at all. The solution is capable of suggesting learning resources, based in a user profile, by combining string similarity techniques, clustering algorithms and filtering techniques.
As more and more digital resources are available, finding the appropriate document becomes harder. Thus, a new kind of tools, able to recommend the more appropriated resources according the user needs, becomes even more necessary. The objective of this I&D work is to implement an intelligent recommendation module (MRI) for e-learning platforms. The recommendations are based on one hand, the performance of the user profile and on the other hand, the requests made by the user in the form of search queries [Tavares, Faria e Martins, 2012]. The e-learning 3.0 is a project developed by a group of organizations and has as primary objective the development of an e-learning platform. This work is inserted in the project e-learning 3.0 being responsible for the MRI. The MRI uses different techniques, which are already being used in recommendation systems, and apply those techniques to create a hybrid tutoring system for an e-learning platform. A user model was built to represent the relevant information about each user. All the information needed to do a recommendation is represented in that model, the model will be updated every time it is necessary. The data in the user model will be used to personalize the produced recommendations. The recommendations are divided into two types, the formal recommendation and the non-formal recommendation. In the formal recommendation the goal is to make suggestions related to a specific course. In the non-formal recommendation the purpose is to make suggestions that are not associated with any course at all. The solution is capable of suggesting learning resources, based in a user profile, by combining string similarity techniques, clustering algorithms and filtering techniques.
Description
Keywords
Modelo de utilizador Sistemas adaptativos Sistemas de recomendaĆ§Ć£o Sistemas de e-learning Query clustering User modeling User-adapted systems Recommending systems E-learning systems
Citation
Publisher
Instituto PolitƩcnico do Porto. Instituto Superior de Engenharia do Porto