The purpose of this study is to examine one of the problems in applying latent Dirichlet allocation (LDA), to poetry works, and to examine the effectiveness of LDA in poetry research. Not only LDA, but also topic modeling in general is considered a promising approach in the field of digital humanities and text mining, and although the number of studies using topic models to study prose works has been increasing in recent years, there have been few studies applying topic models to poetry works. This paper uses the poems of Alfred Tennyson, a Victorian poet, as a target corpus to point out the challenges of applying LDA to verse texts, and to discuss the feasibility of running LDA on texts split into smaller chunks of an equal size.

A database of relevant texts that can be quickly and comprehensively searched is crucial in every field, including literary studies. However, the digital texts available for research in modern-tanka (i.e., a form of Japanese poetry) are insufficient. Additionally, text mining approach has not been used in Japanese literature studies. Thus, a database of modern-tanka texts with search interfaces as a data-curation environment is necessary. Accordingly, we constructed modern-tanka texts into a digital dataset and a full-text modern-tanka database that is now publicly available as the “Kindai Tanka Database.” In this article, we describe the database construction process, the functions of a database, and a modern-tanka case study.

Herein, we introduce a data set containing information interpreted from ancient characters that appear in Chinese excavated materials. This data set has been arranged in a tabular form and is intended to be a comprehensive reference source of the views and interpretations of various researchers. This data set is already available to search in a digital archive of Chinese excavated materials. At present, the only available data are for the excavated Baoshan Chujian（包山楚簡） materials, but we are planning to accumulate more data and expand the target materials in this repository. The current text data on the excavated materials are not yet sufficiently organized, and we hope that this work will serve as a precursor to a more structured data set.