Pemanfaatan Latent Semantic Indexing untuk Mengukur Potensi Kerjasama Jurnal Ilmiah Lintas Universitas

Fernando, Edward Hanafi and Toba, Hapnes (2020) Pemanfaatan Latent Semantic Indexing untuk Mengukur Potensi Kerjasama Jurnal Ilmiah Lintas Universitas. Jurnal Teknik Informatika dan Sistem Informasi, 6 (3). pp. 489-503. ISSN 2443-2229

	Text 13. Pemanfaatan Latent Semantic Indexing untuk Mengukur Potensi Kerjasama Jurnal Ilmiah Lintas Universitas.pdf Download (1905Kb)
	Text Turnitin_ Pemanfaatan Latent Semantic Indexing untuk Mengukur Potensi Kerjasama Jurnal Ilmiah Lintas.pdf Download (4Mb)

Abstract

This paper presents a cooperation recommendation strategy between higher education institutions. The recommendation is based on the contents of journals published in a university journal portal. As a case study, we concentrate our approach for the journals with information technology themes. All journals from 10 reputed universities will be compared by using keywords and the contents of the journal themselves. A partnering recommendation list is built by utilizing Latent Semantic Indexing (LSI). LSI technique is used to reduce the curse of dimensionality from the original dataset and to generate topical analysis from all journals as a semantic representation for each journal. Topic modeling is used to calculate the categorical similarity in the dataset of each university journal and a search query. After all categorical similarities have been calculated, an average value of journal topics coherence is used to construct the final recommendation of partner candidates. This approach ensures that the final recommendation is based on the interest of each university rather than the frequencies of matched keywords in each journal.

Item Type:

Article

Contributors: