Seasonality Pattern of Suicides in the US – a Comparative Analysis of a Twitter Based Bad-mood Index and Committed Suicides

Authors

  • Zoltán Kmetty ELTE-TÁTK MTA-ELTE Peripato Research Group
  • Júlia Koltai MTA-TK ELTE-TÁTK
  • Eszter Bokányi ELTE-TTK
  • Károly Bozsonyi KRE-BTK

DOI:

https://doi.org/10.17356/ieejsp.v3i1.302
Abstract Views: 700 PDF Downloads: 570

Abstract

Is it possible that a general negative social climate exists, which, on the one hand, manifests itself in the number of suicides committed, and on the other hand, appears in the content of tweets posted on social media? In this paper, we are attempting to identify the seasonal and weekly patterns of suicide-related tweets and compare them with similar data that shows the ratios of committed suicides in the US.  For this work we used the data stream freely provided by the online social networking site Twitter to collect geo-located tweets in the US.

In order to calculate the negative mood Twitter–index three terms (words) were used related to suicide (suicide) and bad mood (depression, depressed). The raw daily occurrences of these three words were summarised and then divided by the number of all geo-located daily tweets in the US collected in the framework of the project.

The weekly fluctuation of the temporal distribution of suicides and the ratio of bad mood messages on Twitter fit together well. Tweets show a deterioration of mood on Sundays more intensely; this tendency is more moderate in suicide data. Monthly data, however, are much more challenging to interpret, since the fluctuations show a completely opposite tendency than we expected. We present two possible explanation for this unexpected result.

Downloads

Published

2017-03-29

How to Cite

[1]
Kmetty, Z., Koltai, J., Bokányi, E. and Bozsonyi, K. 2017. Seasonality Pattern of Suicides in the US – a Comparative Analysis of a Twitter Based Bad-mood Index and Committed Suicides. Intersections. East European Journal of Society and Politics. 3, 1 (Mar. 2017). DOI:https://doi.org/10.17356/ieejsp.v3i1.302.

Issue

Vol. 3 No. 1 (2017): The Computational Turn in Social Sciences

Section

The Computational Turn in Social Sciences

License

Copyright Notice

Authors who publish with this journal agree to the following terms:

Authors retain copyright and grant the journal right of first publication, with the work three months after publication simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal. This acknowledgement is not automatic, it should be asked from the editors and can usually be obtained one year after its first publication in the journal.