Summary
International Symposium on Nonlinear Theory and Its Applications
2022
Session Number:B3L-E
Session:
Number:B3L-E-05
Genre Classification of Modern Japanese Literary Works Based on Word Vectors
Shiori Takenaka , Jousuke Kuroiwa , Tomohiro Odaka , Izumi Suwa,
pp.367-370
Publication Date:12/12/2022
Online ISSN:2188-5079
DOI:10.34385/proc.71.B3L-E-05
PDF download (1.1MB)
Summary:
We show that even Japanese literary works by the same writer have different characteristics depending on the genre of the works using word vectors. Because we expect the word vector which quantitatively represent the meaning of the word in a low-dimensional way, are effective enough for expressing the feature of Japanese literary works. The result of the genre classification using word vectors is as accurate as the result of humans classification. Therefore, the word vectors are effective enough for expressing the feature of Japanese literary works.