Applying Part of Speech as indicators for distinguishing corpus type in Digital Humanities Research - A case study of Personal Pronouns, Modal Verbs and Verbs in Chinese Mandarin.

105

Since the early days, information technology has been playing a supporting role in various fields, such as creating databases in various fields, the use of edge detection as the authenticity of paintings, the establishment of different corpus.With the advancement of science and technology, the application of information technology is now more extensive, in which Digital Humanities is a good example. In the field of information science, we use data mining, information retrieval, social network analysis, etc., which have been well-developed, applied in the field of social and humanities science research. In addition to the establishment of a systematic architecture of the historical data for facilitating the retrieval, the text database can help the humanistic researchers to look into their own research from more diverse perspective, in order to achieve more careful research results. In this study, the Acadenia Sinica Balanced Corpus of Modern Chinese, Free China Magazine and the Taiwan Shin Sheng Daily News were used as the research text. This study will focus on the three major Chinese word classes, ie, personal pronouns, modal verbs and verbs, and explore whether the indicators formed by the combination of a single word class, two-word class, and three-word class can make unknown corpus text materials use this study indicators to facilitate follow-up studies.