期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2017
卷号：95
期号：5
出版社：Journal of Theoretical and Applied
摘要：Many texts in online media consist of various information that need an appropriate way to extract and interpret them clearly. For better understanding of the content in the text collected from any online media, a proper methodology for the interpretation of useful information must be developed. This study offers a modified process of the text interpretation consisting of four stages with a preliminary stage of the text preprocessing and key phrase extraction using the annotated suffix tree (AST) technique and secondary stage of developing sparse clustering method named as iterative scaling of fuzzy additive spectral clustering (is-FADDIS) combined with a sharpening technique for grouping key phrases from the text. An ontology as the �knowledge base� was developed combining with is-FADDIS method as the third stage. Interpretation from the input text was carried out as the final stage of the text interpretation. The performances of is-FADDIS clustering combined with sharpening technique as high as 96 and 78% were verified for some modeled sparse data and two specific real sparse data from two corpus, respectively, and could be better when comparing with Nonnegative Matrices Factorization (NMF) and K-means. The text interpretation of using the ontology gives a clear graph visualization on the relationship among key phrases even though it has a low correlation with content of the text. The result findings of this study potentially help us in ensuring an automatic process to be used for the interpretation of any topic information collected from online media.
关键词：Annotated Suffix Tree; is-FADDIS; Ontology; Sparse Clustering; Text Interpretation
