Text Corpus Mining Software MTMineR

• Jin Mingzhe

  Doshisha University

• Zheng Wanwan

  Graduate Student at Doshisha University

Bibliographic Information

Other Title

• テキストコーパスマイニングツールMTMineR

Abstract

MTMineR (Multilingual Text Miner with R) is a free software for the study and education of text corpus mining, which has been in development for nearly 20 years. It transforms unstructured documents in Japanese, Chinese, Korean, English, German, French, and Italian into structured data and then drives R to conduct analyses. All operations are designed to be performed by specifying arguments (if necessary) and pressing buttons. The primary functions include preprocessing, data transformation and data retrieval, and analysis by using various visualization methods, principal component analysis, correspondence analysis, latent topic model, support vector machine, and random forest. Furthermore, MTMineR includes various necessary functions for linguistics and stylistic science research.

Journal

• Mathematical Linguistics

  Mathematical Linguistics 32 (5), 265-276, 2020-06-20

  The Mathematical Linguistic Society of Japan

Keywords

• MTMineR
• Text mining
• Preprocessing
• Data aggregation
• Data retrieval
• Data analysis

Details

• CRID: 1390569923320476160
• NII Article ID: 130008054298
• NII Book ID: AN00073067
• DOI: 10.24701/mathling.32.5_265
• ISSN: 24330302
• ISSN: 04534611
• NDL BIB ID: 030510452
• Web Site: http://id.ndl.go.jp/bib/030510452
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I030510452
• Text Lang: ja
• Data Source:
  • JaLC
  • NDL
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Allowed