• Title/Summary/Keyword: Hierarchical Dustering

Search Result 1, Processing Time 0.017 seconds

A Study of Computational Literature Analysis based Classification for a Pairwise Comparison by Contents Similarity in a section of Tokkijeon, 'Fish Tribe Conference' (컴퓨터 문헌 분석 기반의 토끼전 '어족회의' 대목 내용 유사도에 따른 이본 계통 분류 연구)

  • Kim, Dong-Keon;Jeong, Hwa-Young
    • The Journal of the Korea Contents Association
    • /
    • v.22 no.5
    • /
    • pp.15-25
    • /
    • 2022
  • This study aims to identify the family and lineage of a part of a "Fish Tribe Conference" in the section Tokkijeon by utilizing computer literature analysis techniques. First of all, we encode the classification for a pairwise comparison's type of each paragraph to build a corpus, and based on this, we use the Hamming distance to calculate the distance matrix between each classification for a pairwise comparison's. We visualized classification for a pairwise comparison's clustering pattern by applying multidimensional scale method, and hierarchical clustering to explore the characteristics of the 'fish family' line and lineage compared to the existing cluster analysis study on entire paragraphs of "Tokkijeon". As a result, unlike the cluster analysis of the entire paragraph of "Tokkijeon", which consists of six categories, the "Fish Tribe Conference" section has five categories and some classification for a pairwise comparison's accesses. The results of this study are that the relative distance between Yibon was measured and systematic classification was performed in an objective and empirical way by calculation, and the characteristics of the line of the fish family were revealed compared to the analysis of the entire rabbit exhibition.