Abstract
In literary research, subjective analysis by researchers and critics using artisanal analog methods is still the mainstream approach. In contrast, text-processing techniques that make full use of machine learning are already being actively applied to the analysis of Internet public opinion and various types of reviews. In this study, we analyzed the works of representative writers of modern Japanese literature in terms of emotions and topics. For emotion-based analysis, we combined a dictionary-based emotional analysis technique with the RoBERTa machine learning model. For topic-based analysis, we used a method for clustering distributed representations generated by Sentence-BERT. The method proposed in this study for analyzing the characteristics of literary works using machine learning techniques represents one of the most advanced and objective digital approaches to literary research.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Yoshida, T., Kobayashi, I.: An approach to a bird’s-eye analysis on novels based on emotional expressions. DEIM Forum, A8–6 (2011). (in Japanese)
Kikuchi, Y., Kato, C., Maeshiro, H.: An exploration of the fiction of Murakami Haruki using fuzzy cluster analysis. J. Visual. Soc. Japan 31(Suppl. 1), 141–146 (2011). (in Japanese)
Adachi, Y., Negishi, T.: Development and evaluation of a real-time analysis method for free-description questionnaire responses. In: Proceedings of the 15th IEEE International Conference on Computer Science and Education (2020)
Tsumuraya, K., Takahashi, H., Adachi, Y.: Emotion analysis and topic analysis of Japanese sentences by BERT. In: The 84th National Convention of IPSJ (2022). (in Japanese)
Adachi, Y., Kondo, T., Kobayashi, T., Etani, N., Ishii, K.: Emotion analysis of Japanese sentences using an emotion-word dictionary. J. Visual. Soc. Japan 41(161), 21–27 (2021). (in Japanese)
Seyama, Y., Astremo, A., Adachi, Y.: Extraction of “request” intentions for review analysis on social media and e-commerce sites. In: FIT2021 (2021). (in Japanese)
Yonghui, H., Tsumuraya, K., Uehara, M., Adachi Y.: High-speed emotional analysis of free-descriptive sentences using an emotional-word dictionary. In: IEEE ICCSE2022 (2022)
Tsumuraya, K., Amano, M., Uehara, M., Adachi Y.: Topic-Based Clustering of Japanese Sentences Using Sentence-BERT. CANDAR2022 (2022)
Liu, Y., et al.: RoBERTa: A robustly optimized BERT pretraining approach. arXiv:1907.11692 (2019)
Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using siamese bert-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, (2019). https://arxiv.org/abs/1908.10084
rinna Co., Ltd.: japanese-roberta-base (2022). https://huggingface.co/rinna/japanese-roberta-base. Accessed 29 oct 2022
National Institute of Information and Communications Technology. NICT BERT Japanese Pre-trained models (2022). https://alaginrc.nict.go.jp/nict-bert/index.html. Accessed 29 oct 2022
Yoshikoshi, T., Kawahara, D., Kurohashi, S.: Multilingualization of a Natural Language Inference Dataset Using Machine Translation, SIG Technical Reports, vol. 2020-NL-244 No.6 (2020). (in Japanese)
Devlin, J., Chang M. W., Lee, K., Toutanova, K.: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (2018). arXiv:1810.04805
Japanese Wikipedia (2022). https://dumps.wikimedia.org/jawiki/. Accessed 29 oct 2022
CC-100: Monolingual Datasets from Web Crawl Data (2022). https://data.statmt.org/cc-100/. Accessed 29 oct 2022
Tohoku NLP Group.: Pretrained Japanese BERT models (2022). https://github.com/cl-tohoku/bert-japanese.31 oct 2022
Williams, A., Nangia, N., Bowman, S.: A broad-coverage challenge corpus for sentence understanding through inference. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1, 1112–1122 (Long Papers) (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Amano, M., Tsumuraya, K., Uehara, M., Adachi, Y. (2023). An Analysis of Representative Works of Japanese Literature Based on Emotions and Topics. In: Barolli, L. (eds) Advanced Information Networking and Applications. AINA 2023. Lecture Notes in Networks and Systems, vol 654. Springer, Cham. https://doi.org/10.1007/978-3-031-28451-9_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-28451-9_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-28450-2
Online ISBN: 978-3-031-28451-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)