Advertisement

Deep Learning Algorithm for Suicide Sentiment Prediction

  • Samir BoukilEmail author
  • Fatiha El Adnani
  • Loubna Cherrat
  • Abd Elmajid El Moutaouakkil
  • Mostafa Ezziyyani
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 914)

Abstract

The increasing use of social media provides unprecedented access to the behaviors, thoughts, feelings and intentions of individuals. We are interested, in this paper, in the detection of notes that express bad feelings that might lead to committing suicide. Our goal is to present an automated detection and prediction system capable of recognizing severe depression through analyzing sentiments and feelings expressed on social networks, blogs, emails and even textual notes. In this work, we have set up a chain of treatments to extract characteristics from notes reflecting the emotional state. We can summarize these treatments in two phases: a pretreatment phase based on the Arabic stemming algorithms, and a phase of construction of feature vectors specific to each word of the corpus based on Term Frequency-Inverse Document Frequency method. Then, we applied a model based on Convolutional Neural Networks to predict the nature of feelings behind the note. The Convolutional Neural Network algorithm is one of many famous algorithms of deep learning field. It is originally created for image processing applications. But recently, it is more and more used in text mining and sentiment analysis field. The originality of the approach is, in one hand, to consider both the nature of the words that individuals used to express themselves. And in the other hand, to use the advantages of the Convolutional Neural Network to automatically extract the most significant and reliable features. A preliminary experiment allowed us to evaluate our approach on real cases of online suicidal notes.

Keywords

Suicide Depression Classification Sentiment analysis Deep learning Convolutional Neural Networks Term Frequency-Inverse Document Frequency 

References

  1. 1.
    Burnap, P., Colombo, G., Amery, R., Hodorog, A., Scourfield, J.: Multi-class machine classification of suicide-related communication on Twitter. Online Soc. Netw. Media J. 2, 32–44 (2017).  https://doi.org/10.1016/j.osnem.2017.08.001CrossRefGoogle Scholar
  2. 2.
    Simons, R.L., Murphy, P.I.: Sex differences in the causes of adolescent suicide ideation. J. Youth Adolesc. 14(5) (1985).  https://doi.org/10.1007/BF02138837CrossRefGoogle Scholar
  3. 3.
    Cha, C.B., et al.: Examining potential iatrogenic effects of viewing suicide and self-injury stimuli. Psychol. Assess. J. 28(11), 1510–1515 (2016).  https://doi.org/10.1037/pas0000280CrossRefGoogle Scholar
  4. 4.
    Chatard, A., Selimbegović, L.: When self-destructive thoughts flash through the mind: failure to meet standards affects the accessibility of suicide-related thoughts. J. Personal. Soc. Psychol. 100(4), 587–605 (2011).  https://doi.org/10.1037/a0022461CrossRefGoogle Scholar
  5. 5.
    Birjali, M., Beni-Hssane, A., Erritali, M.: A method proposed for estimating depressed feeling tendencies of social media users utilizing their data. In: Abraham, A., Haqiq, A., Alimi, A.M., Mezzour, G., Rokbani, N., Muda, A.K. (eds.) Proceedings of the 16th International Conference on Hybrid Intelligent Systems (HIS 2016), Marrakech, Morocco. Advances in Intelligent Systems and Computing, vol. 552, pp. 413–420. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-52941-7_41Google Scholar
  6. 6.
    Kasturi, D.V., Nurhafizah, T.: Suicide detection system based on twitter. In: Science and Information Conference, London, UK, pp. 785–788. IEEE (2014).  https://doi.org/10.1109/sai.2014.6918275
  7. 7.
    Gualtiero, B., Colombo, P., Burnapa, A., Hodorog, J.S.: Analysing the connectivity and communication of suicidal users on twitter. Comput. Commun. 73, 291–300 (2016).  https://doi.org/10.1016/j.comcom.2015.07.018CrossRefGoogle Scholar
  8. 8.
    Gonzalez-Marron, D., Mejia-Guzman, D., Enciso-Gonzalez, A.: Exploiting data of the Twitter social network using sentiment analysis. In: Sucar, E., Mayora, O., Munoz de Cote, E. (eds.) Applications for Future Internet. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol. 179. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-49622-1_5Google Scholar
  9. 9.
    Spasic, I., Burnap, P., Greenwood, M., Arribas, M.A.: A Naïve Bayes approach to classifying topics in suicide notes. Biomed. Inform. Insights 5(1), 87–97 (2012).  https://doi.org/10.4137/bii.s8945CrossRefGoogle Scholar
  10. 10.
    Schoene, A.M., Dethlefs, N.: Automatic identification of suicide notes from linguistic and sentiment features. In: Proceedings of the 10th SIGHUM Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities, Berlin, Germany, pp. 128–133. Association for Computational Linguistics (2016).  https://doi.org/10.18653/v1/w16-2116
  11. 11.
    Singh, J., Singh, G., Singh, R., Singh, P.: Morphological evaluation and sentiment analysis of Punjabi text using deep learning classification. J. King Saud Univ. Comput. Inf. Sci. (2018).  https://doi.org/10.1016/j.jksuci.2018.04.003
  12. 12.
    Alam, M.H., Rahoman, M.-M., Azad, M.A.K.: Sentiment analysis for Bangla sentences using convolutional neural network. In: The 20th International Conference of Computer and Information Technology (ICCIT), Dhaka, Bangladesh, pp. 1–6. IEEE (2017). https://doi.org/10.1109/iccitechn.2017.8281840
  13. 13.
    Billot, R., Berrouiguet, S., Larsen, M., Walter, M., Castroman, J.L., García, E.B., Courtet, P., Lenca, P.: Providing data mining for suicidal risk prevention. Apport de la fouille de données pour la prévention du risque suicidaire. In: Proceedings of International Conference on Extraction and Knowledge Management, vol. RNTI-E-34, Magazine of New Information Technologies, Paris, France, pp. 143–154 (2018)Google Scholar
  14. 14.
    Poulin, C., et al.: Predicting the risk of suicide by analyzing the text of clinical notes. PLoS ONE 9(1) (2014).  https://doi.org/10.1371/journal.pone.0085733CrossRefGoogle Scholar
  15. 15.
    Gunn, J.F., Lester, D.: Twitter postings and suicide: an analysis of the postings of a fatal suicide in the 24 h prior to death. Suicidologi 17(3), 28–30 (2012)Google Scholar
  16. 16.
    Sueki, H.: The association of suicide-related twitter use with suicidal behavior: a cross sectional study of young internet users in japan. J. Affect. Disord. 170(1), 155–160 (2015).  https://doi.org/10.1016/j.jad.2014.08.047CrossRefGoogle Scholar
  17. 17.
    Karmen, C., Hsiung, R.C., Wetter, T.: Screening internet forum participants for depression symptoms by assembling and enhancing multiple NLP methods. Comput. Methods Programs Biomed. J. 120(1), 27–36 (2015).  https://doi.org/10.1016/j.cmpb.2015.03.008CrossRefGoogle Scholar
  18. 18.
    Bahassine, S., Kissi, M., Madani, A.: Arabic text classification using new stemmer for feature selection and decision trees. J. Eng. Sci. Technol. 12(6), 1475–1487 (2017)Google Scholar
  19. 19.
    Larkey, L.S., Ballesteros, L., Connell, M.: Improving stemming for Arabic information retrieval: light stemming and cooccurrence analysis. In: The 25th Annual International Conference on Research and Development in Information Retrieval (SIGIR 2002), Tampere, Finland, pp. 275–282 (2002)Google Scholar
  20. 20.
    Salton, G., Buckley, C.: Term-weighing approach in automatic text retrieval. Inf. Process. Manag. 24(5), 513–523 (1988).  https://doi.org/10.1016/0306-4573(88)90021-0CrossRefGoogle Scholar
  21. 21.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems, NIPS 2012, Lake Tahoe, Nevada, vol. 1, pp. 1097–1105. IEEE (2012).  https://doi.org/10.1145/3065386CrossRefGoogle Scholar
  22. 22.
    Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998).  https://doi.org/10.1109/5.726791CrossRefGoogle Scholar
  23. 23.
    Al-Zaghoul, F., Al-Dhaheri, S.: Arabic text classification based on features reduction using artificial neural networks. In: The 15th International Conference on Computer Modelling and Simulation (UKSim), Cambridge University, United Kingdom, pp. 485–490. IEEE (2013).  https://doi.org/10.1109/uksim.2013.135
  24. 24.
    WEKA: A machine learning tool set. http://www.cs.waikato.ac.nz/ml/weka/index_downloading.html. Accessed 9 Aug 2018

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Samir Boukil
    • 1
    Email author
  • Fatiha El Adnani
    • 1
  • Loubna Cherrat
    • 1
  • Abd Elmajid El Moutaouakkil
    • 1
  • Mostafa Ezziyyani
    • 2
  1. 1.Laboratory (LAROSERI), Department of Computer, Faculty of SciencesChouaib Doukkali UniversityEl JadidaMorocco
  2. 2.Faculty of Sciences and TechnologiesAbdelmalek Essaadi UniversityTangierMorocco

Personalised recommendations