Abstract
In recent years, text analysis has been applied to newspaper articles in order to analysis social issues. However, it is difficult to identify a specific theme and to show trend using text analysis alone. This study applies deep machine learning to the huge amount of text data available and clarifies social issues and their temporal change by focusing on the social issues of disaster prevention in Japan. We extracted words of the text of newspaper article data about disaster prevention, and applied the skip-gram approach of word2vec to calculate the similarity with a specific keyword that was specified in advance. Next, by applying Non-negative Matrix Factorization (NMF), we performed clustering of words based on the degree of similarity of them and estimated the characteristics of the transition of each cluster. The characteristic result comparing evacuation with volunteers is the content of the agendas in the middle stage (2006–2010) and the final stage (2011–2014). In the middle stage, evacuation was characterized by education, whereas volunteers were characterized by disaster experience. In the final stage, evacuation was characterized by system issues, while volunteers were characterized by education and operation.
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
Thompson-Saud, G., Gelcich, S., Barraza, J.: Marine environmental issues in the mass media: Insights from television, newspaper and internet searches in Chile. Ocean Coastal Manage. 165, 154–160 (2018). https://doi.org/10.1016/j.ocecoaman.2018.08.015
Ho, G.W.K., Chan, A.C.Y.: Media portrayal of a hidden problem: an analysis of Hong Kong newspaper coverage of child maltreatment in. Child Abuse Negl. 83, 62–73 (2016). https://doi.org/10.1016/j.chiabu.2018.07.002(2018)
Du, Q., Han, Z.: The framing of nuclear energy in Chinese media discourse: A comparison between national and local newspapers. J. Cleaner Prod. 245 (2020). https://doi.org/10.1016/j.jclepro.2019.118695
Chosokabe, M., Takeyoshi, H., Sakakibara, H.: Study on temporal change of social context. In: The case of Bicycle Riding Issue in Japan, Proceedings of the 2014 Group Decision and Negotiation, pp. 315–322 (2014)
Prince, V.: Social identification and public opinion: effects of communicating group conflict. Am. Assoc. Public Opinion Res. 53(2), 197–224 (1989)
Brains, L.C., Wattenberg, P.M.: Campaign issue knowledge and salience: comparing reception from TV commercials. TV News Newspapers 40(1), 172–193 (1996)
Tokui, J., Kawasaki, K., Miyagawa, T.: The economic impact of supply chain disruptions from the Great East-Japan earthquake. Japan World Econ. 41, 59–70 (2017). https://doi.org/10.1016/j.japwor.2016.12.005
Kondo, A.: The effects of supply chain disruptions caused by the Great East Japan earthquake on workers. Japan World Econ. 47, 40–50 (2018). https://doi.org/10.1016/j.japwor.2018.03.007
Garg, N., Schiebinger, L., Jurafsky, D., Zou, J.: Word embeddings quantify 100 years of gender and ethnic stereotypes. PNAS, 115(16), E3635–E3644 (2018). https://doi.org/10.1073/pnas.1720347115
Chosokabe, M., Umeda, H., Sakakibara, H.: The contribution of social context to participatory planning processes within a Japanese community. Group Decis. Negot. 25(5), 923–940 (2015). https://doi.org/10.1007/s10726-015-9466-2
Chosokabe, M., Sakamoto, M., Tanimoto, K.: Comparative study of local and national newspapers: a case study of the reconstruction in response to the great East Japan Earthquake. In: Proceedings of the 2018 Group Decision and Negotiation, pp. 91–98 (2018)
Silge, J., Robinson, D.: Text Mining with R: Tidy Approach, 6 Topic modeling (2021). https://www.tidytextmining.com/topicmodeling.html
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: Proceedings of Workshop at International Conference on Learning Representations (ICLR). arXiv:1301.3781 (2013)
Szymanski, T.: Temporal word analogies: identifying lexical replacement with diachronic word embeddings. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Short Papers), pp. 448–453 (2017). https://doi.org/10.18653/v1/P17-2071
Sasaki, D.: The basic trend of media reports on residents’ return in Fukushima: in the realms of text mining analysis. J. Asian Dev. 3(1), 65–72 (2017). https://doi.org/10.5296/jad.v3i1.10572
Goldberg, Y., Levy, O.: word2vec Explained: deriving Mikolov et al.’s negative-sampling word-embedding method. arXiv:1402.3722 (2014)
Paatero, P., Tapper, U.: Positive matrix factorization: a non-negative factor model with optimal utilization of error estimates of data values. Environmetrics 5(2), 111–126 (1994)
Lee, D.D., Seung, H.S.: Learning the parts of objects by non-negative matrix factorization. Nature 401, 788–791 (1999)
Lee, D.D., Seung, H.S.: Algorithms for non-negative matrix factorization. Adv. Neural Inf. Process. Syst. 13(1) (2001)
Acknowledgment
This study was funded by JSPS KAKENHI Grant Number JP18K13851.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Chosokabe, M., Tanimoto, K., Tsuchiya, S. (2021). Analysis on the Temporal Transition of Social Issues Related to Disaster Prevention Using Text Data. In: Morais, D.C., Fang, L., Horita, M. (eds) Contemporary Issues in Group Decision and Negotiation. GDN 2021. Lecture Notes in Business Information Processing, vol 420. Springer, Cham. https://doi.org/10.1007/978-3-030-77208-6_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-77208-6_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-77207-9
Online ISBN: 978-3-030-77208-6
eBook Packages: Computer ScienceComputer Science (R0)