TY - JOUR
T1 - Social web content enhancement in a distance learning environment
T2 - Intelligent metadata generation for resources
AU - García-Floriano, Andrés
AU - Ferreira-Santiago, Angel
AU - Yáñez-Márquez, Cornelio
AU - Camacho-Nieto, Oscar
AU - Aldape-Pérez, Mario
AU - Villuendas-Rey, Yenny
PY - 2017
Y1 - 2017
N2 - Social networking potentially offers improved distance learning environments by enabling the exchange of resources between learners. The existence of properly classified content results in an enhanced distance learning experience in which appropriate materials can be retrieved efficiently; however, for this to happen, metadata needs to be present. As manual metadata generation is time-costly and often eschewed by the authors of the social web resources, automatic generation is a fertile area for research as several kinds of metadata, such as author or topic, can be generated or extracted from the contents of a document. In this paper we propose a novel metadata generation system aimed at automatically tagging distance learning resources. This system is based on a recently-created intelligent pattern classifier; specifically, it trains on a corpus of example documents and then predicts the topic of a new document based on its text content. Metadata is generated in order to achieve a better integration of the web resources with the social networks. Experimental results for a two-class problem are promising and encourage research geared towards applying this method to multiple topics.
AB - Social networking potentially offers improved distance learning environments by enabling the exchange of resources between learners. The existence of properly classified content results in an enhanced distance learning experience in which appropriate materials can be retrieved efficiently; however, for this to happen, metadata needs to be present. As manual metadata generation is time-costly and often eschewed by the authors of the social web resources, automatic generation is a fertile area for research as several kinds of metadata, such as author or topic, can be generated or extracted from the contents of a document. In this paper we propose a novel metadata generation system aimed at automatically tagging distance learning resources. This system is based on a recently-created intelligent pattern classifier; specifically, it trains on a corpus of example documents and then predicts the topic of a new document based on its text content. Metadata is generated in order to achieve a better integration of the web resources with the social networks. Experimental results for a two-class problem are promising and encourage research geared towards applying this method to multiple topics.
KW - Distance learning
KW - Intelligent classification
KW - Metadata generation
KW - Social networking
KW - Social web content
UR - http://www.scopus.com/inward/record.url?scp=85014094089&partnerID=8YFLogxK
U2 - 10.19173/irrodl.v18i1.2646
DO - 10.19173/irrodl.v18i1.2646
M3 - Artículo
SN - 1492-3831
VL - 18
SP - 161
EP - 176
JO - International Review of Research in Open and Distance Learning
JF - International Review of Research in Open and Distance Learning
IS - 1
ER -