The Basic Trend of Media Reports on Residents’ Return in Fukushima: In the Realms of Text Mining Analysis

Daisuke Sasaki


In general, people’s concerns appear to be represented through the mass media. In the Great East Japan Earthquake and the nuclear power station accident in Fukushima prefecture, the many reports made by the mass media provide enough information that we can understand the overall situation. In this context, examining reports by the mass media concerning this issue can be thought of as an analysis of stakeholders’ concerns. However, it is of great significance to verify whether reports by the mass media correctly reflect people’s concerns or not. I analyzed Japanese text data from the Fukushima local newspaper using a text mining methodology, and have confirmed the general accuracy of media reports with respect to evacuees’ concerns. I also found that in media reports the biggest issue related to residents returning to their homes seemed to be their livelihoods, whereas matters related to the Fukushima Daiichi Nuclear Power Station were rarely reported in connection with residents’ return. Therefore, the most effective measure for having evacuees willingly return to their homes may be to address their anxieties about daily life including the employment environment with high priority so that evacuees can return to their homes willingly.

Full Text:



Fukushima Prefecture. (2016). Transition of evacuation instruction zones. Retrieved from (January 1, 2017).

Goldberg, Y., & Levy, O. (2014). Word2vec explained: Deriving Mikolov et al.’s negative-sampling word-embedding method. arXiv:1402.3722 [cs, stat]. arXiv: 1402.3722.

Heuer, H. (2015). Text comparison using word vector representations and dimensionality reduction. Proceedings of the 8th European Conference on Python in Science (EuroSciPy 2015), 13-16.

Hirono Town. (2013). The results of the survey on townpeople’s intentions for developing the Second Hirono Revitalization Plan. Fukushima, Japan: Hirono Town. (Japanese).

Hirono Town. (2014). The report on the survey on the development of Hirono Town by Hirono Town Development Board. Fukushima, Japan: Hirono Town. (Japanese).

Hirono Town. (2016). Census registration information of Hirono Town. Retrieved from (January 1, 2017) (Japanese).

Li, Y., Zheng, R., Tian, T., Hu, Z., Iyer, R., & Sycara, K. (2016). Joint embedding of hierarchical categories and entities for Concept Categorization and Dataless Classification. Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, 2678–2688.

Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013a). Efficient estimation of word representations in vector space. ICLR Proceeding of the International Conference on Learning Representations Workshop Track. arXiv:1301.3781 [cs.CL]

Mikolov, T., Yih, W., & Zweig, G. (2013b). Linguistic regularities in continuous space word representations. Proceedings of North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 746–751.

Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013c). Distributed representations of words and phrases and their compositionality. Proceedings of Advances in Neural Information Processing Systems, 3111–3119.

Van der Maaten, L., & Hinton, G. (2008). Visualizing high-dimensional data using t-SNE. Journal of Machine Learning Research, 9, 2579–2605.

Van der Maaten, L. (2014). Accelerating t-SNE using tree-based algorithms. Journal of Machine Learning Research, 15, 3221–3245.



  • There are currently no refbacks.

Journal of Asian Development  ISSN 2377-9594   E-mail:

Copyright © Macrothink Institute 

To make sure that you can receive messages from us, please add the '' domains to your e-mail 'safe list'. If you do not receive e-mail in your 'inbox', please check your 'spam' or 'junk' folder.