저자 기반 코퍼스 구축과 분석 도구 개발

Construction of Author-based Corpus and Development of Analysis Tools

초록

In this study, we constructed author-based corpus for authorship contribution research and developed analysis tool to utilize the corpus. In addition, a case study on how to use the constructed author-based corpus and analysis tool is presented. The author-based corpus constructed in this study contains 800 column data, and the name of the corpus is H-column corpus. The analysis tool developed in this study was developed for the analysis of frequencies of morphemes and parts of speech. The name of the analysis tool was Knalyzer 2.0. In addition, we developed the Gonapps consonant-vowel analyzer to enable N-gram analysis of the authors in the authorship contribution. Finally, using these corpus and analysis tools, we proposed how to apply it to the study of lexical richness, which is one of the important themes of the authorship contribution research.

키워드

Authorship contributionAuthor-based corpusMorpheme frequencyParts of speech frequencyFrequency by sectionConsonant-vowel analyzerLexical richnessH-Column CorpusKnalyzer 2.0저자 판별저자 기반 코퍼스형태소 빈도 분석품사 빈도 분석구간별 빈도 분석자모 분석기어휘 풍부성H-Column Corpus(HCC)Knalyzer 2.0Gonapps 자모 분석기
제목
저자 기반 코퍼스 구축과 분석 도구 개발
제목 (타언어)
Construction of Author-based Corpus and Development of Analysis Tools
저자
임현열
DOI
10.33252/sih.2018.03.56.235
발행일
2018
저널명
인문과학연구
56
페이지
235 ~ 254