Abstract
The 2011 Great East Japan Earthquake and 2016 Kumamoto earthquakes had a great impact on numerous people all over the world. In this paper, we focus on social media and the mental health of 2016 Kumamoto earthquake survivors. We first focus on the users who had experienced an earthquake and track their sentiments before and after the disaster using Twitter as a sensor. Consequently, we found that their emotional polarities switch from nervous during earthquakes and return to normal after huge earthquakes. However, we also found that some people did not go back to normal even after huge earthquakes subside. Against this background, we attempted to identify survivors who are suffering from serious mental distress concerning earthquakes. Our experimental results suggest that, besides the frequency of words related to earthquakes, the deviation in sentiment and lexical factors during the earthquake represent the mental conditions of Twitter users. We believe that the findings of this study will contribute to early mental health care for people suffering the aftereffects of a huge disaster.
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
Similar content being viewed by others
Notes
- 1.
IBM®Watson Explorer Advanced Edition Analytical Components V11.0 is a trademark in the United States and/or other countries of International Business Machines Corporation.
- 2.
We extracted expressions which occur with high frequency and correlation by using WEX and defined them as earthquake-related words:
 (earthquake), 
 (aftershock), 
 (immediate report), 
 (shelter), 
 (shaking) and 
 (goods). - 3.
The actual annotation was a three class label: a user who does not care about the disaster, a user who is slightly concerned with the disaster, and user who is severely affected by the disaster. This annotation was conducted by two human annotators, and Cohen’s kappa for that is 0.75. By merging the first two classes into one class, we created an experimental dataset with two classes.
- 4.
References
Aramaki, E., Maskawa, S., Morita, M.: Twitter catches the flu: detecting influenza epidemics using Twitter. In: Proceedings of EMNLP 2011, pp. 1568–1576 (2011)
Backstrom, L., Sun, E., Marlow, C.: Find me if you can: improving geographical prediction with social and spatial proximity. In: Proceedings of WWW 2010, pp. 61–70 (2010)
Choudhury, M.D., Counts, S., Horvitz, E.: Predicting postpartum changes in emotion and behavior via social media. In: Proceedings of CHI 2013, pp. 3267–3276 (2013)
Choudhury, M.D., Gamon, M., Counts, S., Horvitz, E.: Predicting depression via social media. In: Proceedings of ICWSM 2013 (2013)
Coppersmith, G., Dredze, M., Harman, C.: Quantifying mental health signals in Twitter. In: Proceedings of Workshop on Computational Linguistics and Clinical Psychology, pp. 51–60 (2014)
Coppersmith, G., Dredze, M., Harman, C., Hollingshead, K.: From ADHD to SAD: analyzing the language of mental health on Twitter through self-reported diagnoses. In: Proceedings of Workshop on Computational Linguistics and Clinical Psychology, pp. 1–10 (2015)
Gkotsis, G., Oellrich, A., Hubbard, T., Dobson, R., Liakata, M., Velupillai, S., Dutta, R.: The language of mental health problems in social media. In: Proceedings of Workshop on Computational Linguistics and Clinical Psychology, pp. 63–73 (2016)
Higashiyama, M., Inui, K., Matsumoto, Y.: Learning sentiment of nouns from selectional preferences of verbs and adjectives. In: Proceedings of Annual Meeting of the Association for Natural Language Processing (in Japanese), pp. 584–587 (2008)
Kumar, M., Dredze, M., Coppersmith, G., Choudhury, M.D.: Detecting changes in suicide content manifested in social media following celebrity suicides. In: Proceedings of HT 2015, pp. 85–94 (2015)
Lamb, A., Paul, M.J., Dredze, M.: Separating fact from fear: tracking flu infections on Twitter. In: Proceedings of NAACL:HLT 2013, pp. 789–795 (2013)
Lin, H., Jia, J., Nie, L., Shen, G., Chua, T.: What does social media say about your stress? In: Proceedings of IJCAI 2016, pp. 3775–3781 (2016)
Neubig, G., Matsubayashi, Y., Hagiwara, M., Murakami, K.: Safety information mining-what can NLP do in a disaster-. In: Proceedings of IJCNLP 2011, pp. 965–973 (2011)
O’Connor, B., Balasubramanyan, R., Routledge, B.R., Smith, N.A.: From tweets to polls: linking text sentiment to public opinion time series. In: Proceedings of ICWSM 2010, pp. 23–26 (2010)
Okazaki, N., Nabeshima, K., Watanabe, K., Mizuno, J., Inui, K.: Extracting and aggregating false information from microblogs. In: Proceedings of Workshop on Language Processing and Crisis Information, pp. 36–43 (2013)
Pennebaker, J.W., Francis, M.E., Booth, R.J.: Linguistic inquiry and word count: LIWC 2001. Lawrence Erlbaum Associates (2001)
Sakaki, T., Okazaki, M., Matsuo, Y.: Earthquake shakes Twitter users: real-time event detection by social sensors. In: Proceedings of WWW 2010, pp. 851–860 (2010)
Takamura, H., Inui, T., Okumura, M.: Extracting semantic orientations of words using spin model. In: Proceedings of ACL 2005, pp. 133–140 (2005)
Varga, I., Sano, M., Torisawa, K., Hashimoto, C., Ohtake, K., Kawai, T., Oh, J.H., De Saeger, S.: Aid is out there: looking for help from tweets during a large scale disaster. In: Proceedings of ACL 2013, pp. 1619–1629 (2013)
Vieweg, S., Hughes, A.L., Starbird, K., Palen, L.: Microblogging during two natural hazards events: what Twitter may contribute to situational awareness. In: Proceedings of CHI 2010, pp. 1079–1088 (2010)
Acknowledgements
We are grateful to Koichi Kamijoh, Hiroshi Kanayama, Masayasu Muraoka, and the members of the IBM Research - Tokyo text mining team for their helpful discussions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Aoki, T., Yoshikawa, K., Nasukawa, T., Takamura, H., Okumura, M. (2018). Detecting Earthquake Survivors with Serious Mental Affliction. In: Hasida, K., Pa, W. (eds) Computational Linguistics. PACLING 2017. Communications in Computer and Information Science, vol 781. Springer, Singapore. https://doi.org/10.1007/978-981-10-8438-6_1
Download citation
DOI: https://doi.org/10.1007/978-981-10-8438-6_1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-8437-9
Online ISBN: 978-981-10-8438-6
eBook Packages: Computer ScienceComputer Science (R0)