TY - CHAP
T1 - Proactive sequencing based on a causal and fuzzy student model
AU - Peña-Ayala, Alejandro
AU - Sossa, Humberto
PY - 2013
Y1 - 2013
N2 - Proactive education paradigm pursues to infer future possible events and states of the teaching-learning cycle to accomplish better students' apprenticeship, and overcome likely issues. An essential functionality to implement such a paradigm is the prediction. Thus, our approach aims at anticipating student's domain knowledge (DK) acquisition through the development, and use of a causal and fuzzy student model (CFSM). The CFSM depicts several domains of student's attributes, that are taken into account for sequencing lectures to students. Moreover, it also characterizes attributes of the content, to shape the nature of the available lectures authored to teach a given concept. Both sorts of attributes are defined semantically as concepts in an ontology. These concepts set causal relationships between each other. This type of relationships represents a belief of how an attribute exerts the status and activation of another attribute. Concepts and causal relationships are sketched as a cognitive map (CM). The description of the attributes and the causal relationships are respectively made by fuzzy values and fuzzy rules-bases. Linguistic terms instantiate the state of concepts and a version of fuzzy-causal inference is fulfilled to produce causal behavior and outcomes about the state of the concepts. Based on these elements, our approach simulates the learning results that a lecture could produce on student's apprenticeship. Such a prediction is accounted to choose the most profitable lecture for being delivered to student. As a result of an experiment, we found out those users of a web-based educational system (WBES) that sequences lectures based on the advice given by the CFSM reached 17% higher learning than their peers who did not have the support of our approach. So in this work, we highlight the attributes of the approach.
AB - Proactive education paradigm pursues to infer future possible events and states of the teaching-learning cycle to accomplish better students' apprenticeship, and overcome likely issues. An essential functionality to implement such a paradigm is the prediction. Thus, our approach aims at anticipating student's domain knowledge (DK) acquisition through the development, and use of a causal and fuzzy student model (CFSM). The CFSM depicts several domains of student's attributes, that are taken into account for sequencing lectures to students. Moreover, it also characterizes attributes of the content, to shape the nature of the available lectures authored to teach a given concept. Both sorts of attributes are defined semantically as concepts in an ontology. These concepts set causal relationships between each other. This type of relationships represents a belief of how an attribute exerts the status and activation of another attribute. Concepts and causal relationships are sketched as a cognitive map (CM). The description of the attributes and the causal relationships are respectively made by fuzzy values and fuzzy rules-bases. Linguistic terms instantiate the state of concepts and a version of fuzzy-causal inference is fulfilled to produce causal behavior and outcomes about the state of the concepts. Based on these elements, our approach simulates the learning results that a lecture could produce on student's apprenticeship. Such a prediction is accounted to choose the most profitable lecture for being delivered to student. As a result of an experiment, we found out those users of a web-based educational system (WBES) that sequences lectures based on the advice given by the CFSM reached 17% higher learning than their peers who did not have the support of our approach. So in this work, we highlight the attributes of the approach.
UR - http://www.scopus.com/inward/record.url?scp=84879320791&partnerID=8YFLogxK
U2 - 10.1007/978-3-642-30171-1_3
DO - 10.1007/978-3-642-30171-1_3
M3 - Capítulo
AN - SCOPUS:84879320791
SN - 9783642301704
T3 - Smart Innovation, Systems and Technologies
SP - 49
EP - 76
BT - Intelligent and Adaptive Educational-Learning Systems
A2 - Pena-Ayala, Alejandro
ER -