—To solve the problem that the distance education
inevitably produced the “isolated” learners, the learners with
the same interest are organized into the same community for
collaborative learning. In view of neglecting the semantic
relevance between terms of the traditional vector space model,
the vector space model based on ontology is proposed to
calculate the learner's interest eigenvector, and the
corresponding explicit express can be obtained according to the
recessive expression, which improves the accuracy of the
interest similarity comparison. At the same time, a
self-organization algorithm based on the similarity
match-degree and matching concentration of learner's interest
for the learning community is put forward. Great dimensions
would take place with the ontology to construct vector space,
thus Concept Indexing method is adopted to reasonably reduce
the dimensionality of interest characteristic matrix so that
greatly reduces the computational complexity. Finally, an
experimental analysis of online education cases indicates that
the algorithm has high efficiency and good extensibility.
—Ontology, vector space model, concept
indexing method, interest similarity match-degree.
Yan Cheng is with Tongji University. She is also with Jiangxi Normal
University, Nanchang, Jiangxi, China (e-mail: email@example.com).
Yongchun Miao is with Jiangxi Normal University, School of Computer
Information Engineering, Nanchang, China.
Cite: Yan Cheng and Yongchun Miao, "A Novel Grouping Method of Learning Community Based on Interests," International Journal of Information and Education Technology vol. 7, no. 1, pp. 27-34, 2017.