Abstract
In this chapter, the study investigates correlations between excess demand for used cars and topics on Twitter after the Great East Japan Earthquake and Tsunami. Based on the methodology described in Chap. 3, the author conducts Latent Dirichlet Allocation (LDA) with Twitter data after the Great East Japan Earthquake and Tsunami of 2011 and addresses whether topics frequency ratios are correlated with socio-economic activities as reflected in the excess demand for used cars. The findings of this chapter suggest that when there were more communications related to recovery and disaster damages among tweets posted by people who are local to the disaster-stricken area, there may have been more socio-economic activities in the disaster area. In contrast, when there were more communications related to evacuation, there may have been less demand for used cars. Furthermore, among tweets posted by people who are not local to the disaster-stricken area, when there was more communication about going to and supporting the disaster-stricken area, there may have been more socio-economic activities in the disaster-stricken area. The chapter is constructed as the follows: First, the author defines the research topics of this chapter in Sect. 7.1. In Sect. 7.2, the data for this chapter’s analysis will be described. In Sect. 7.3, the model is introduced and the results are shown in Sect. 7.4. Lastly, the author discusses the result in Sect. 7.5 and conclude this chapter in Sect. 7.6.
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
Notes
- 1.
This chapter is a revised version of Shibuya and Tanaka (2019).
- 2.
The author collected this data through an Internet service called Kuchikomi@kakaricho (https://service.hottolink.co.jp/service/kakaricho/).
- 3.
The author manually checked multiple types of tweets that are relevant to the Great East Japan Earthquake and Tsunami and used-car demand and carefully chose the keywords for collecting tweets.
- 4.
This study uses tsunami-stricken cities’ names listed on “Area of inundated area” by the Geospatial Information Authority of Japan (http://www.gsi.go.jp/kikaku/kikaku60004.html, accessed December 12th, 2018, in Japanese). The author only used tsunami-stricken cities’ names in Miyagi and Iwate prefectures. Fukushima prefecture is also one of the devastated areas of the disaster, but this study did not include cities in Fukushima prefecture because Fukushima prefecture suffered more from the Nuclear incident and thus, should be treated differently.
- 5.
Real prices of the used cars were calculated based on the “automobile” deflator of the fiscal 2015 Consumer Price index (CPI) (http://www.stat.go.jp/english/data/cpi/index.html, accessed October 19, 2018).
- 6.
The workshop was conducted as WS-C of the Graduate Program for Social ICT Global Creative Leaders, in which the author participates (Shibuya 2018).
- 7.
To decide a suitable number of topics, the author applied LDA with several topic numbers, including 10, 20, 30, 50 and 100. As a result, when the topic number is 10, the results are most convincing and understandable to people although the perplexity is not the best.
- 8.
For example, in this study, the topic frequency ratio of the second half of April 2011 corresponds to the used-car data of the second half of May 2011.
References
Bica, M., Palen, L., & Bopp, C. (2017). Visual representations of disaster. In Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing - CSCW’17 (pp. 1262–1276). https://doi.org/10.1145/2998181.2998212.
Blei, D. (2012). Probabilistic topic models. Communications of the ACM, 55(4), 77. https://doi.org/10.1145/2133806.2133826.
Shibuya, Y. (2018). How can we leverage social media data for sensing a large-scale disaster recovery status? http://gcl-gdws.org/workshopc/2018%E5%A4%A7%E8%A6%8F%E6%A8%A1%E7%81%BD%E5%AE%B3%E6%99%82%E3%81%AE%E3%82%BD%E3%83%BC%E3%82%B7%E3%83%A3%E3%83%AB%E3%83%A1%E3%83%87%E3%82%A3%E3%82%A2%E6%B4%BB%E7%94%A8%E3%81%AB%E9%96%A2%E3%81%99%E3%82%8B/.
Shibuya, Y., & Tanaka, H. (2019). Detecting disaster recovery activities via social media communication topics. In Proceedings of the 16th International Conference on Information Systems for Crisis Response and Management (ISCRAM 2019), Valencia, Spain.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Shibuya, Y. (2020). Topics on Twitter and the Excess Demand for Used Cars. In: Social Media Communication Data for Recovery. Springer, Singapore. https://doi.org/10.1007/978-981-15-0825-7_7
Download citation
DOI: https://doi.org/10.1007/978-981-15-0825-7_7
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-0824-0
Online ISBN: 978-981-15-0825-7
eBook Packages: Business and ManagementBusiness and Management (R0)