Advertisement

Adapting Models for the Case of Early Risk Prediction on the Internet

  • Razan MasoodEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11438)

Abstract

Internet users who suffer from variant types of mental disorders found in Social Media platforms and other online communities an easier way to reveal their minds. The textual content produced by such users proved to be handful in evaluating mental health and detecting related illnesses even in early stages. This paper overviews my recent doctoral work on eRisk 2019 shared task for early detection of Anorexia and early detection of Self-harm. These sub-tasks have many aspects to consider, including textual content, timing, and the similarities to other mental health prediction tasks. Thus, based on these different dimensions, we propose solutions based on Neural-Networks, Multi-task learning, domain adaptation and Markov Models.

Keywords

Mental health Anorexia Self-harm NLP Machine learning 

References

  1. 1.
    Benton, A., Mitchell, M., Hovy, D.: Multi-task learning for mental health using social media text. arXiv preprint arXiv:1712.03538 (2017)
  2. 2.
    Coopers, P.: The Costs of Eating Disorders Social, Health and Economic Impacts. B-eat, Norwich (2015)Google Scholar
  3. 3.
    Corcoran, C.M., et al.: Prediction of psychosis across protocols and risk cohorts using automated language analysis. World Psychiatry 17(1), 67–75 (2018)CrossRefGoogle Scholar
  4. 4.
    Dungs, S., Aker, A., Fuhr, N., Bontcheva, K.: Can rumour stance alone predict veracity? In: Proceedings of the 27th International Conference on Computational Linguistics, pp. 3360–3370 (2018)Google Scholar
  5. 5.
    Guillaume, S., et al.: Characteristics of suicide attempts in anorexia and bulimia nervosa: a case-control study. PLoS One 6(8), e23578 (2011)CrossRefGoogle Scholar
  6. 6.
    Guillaume, S., et al.: Characteristics of suicide attempts in anorexia and bulimia nervosa: a case-control study. PloS One 6, e23578 (2011)CrossRefGoogle Scholar
  7. 7.
    Juarascio, A.S., Shoaib, A., Timko, C.A.: Pro-eating disorder communities on social networking sites: a content analysis. Eat. Disord. 18(5), 393–407 (2010)CrossRefGoogle Scholar
  8. 8.
    Kshirsagar, R., Morris, R., Bowman, S.: Detecting and explaining crisis. In: Proceedings of the Fourth Workshop on Computational Linguistics and Clinical Psychology - From Linguistic Signal to Clinical Reality, pp. 66–73. Association for Computational Linguistics (2017)Google Scholar
  9. 9.
    Losada, D.E., Crestani, F.: A test collection for research on depression and language use. In: Fuhr, N., et al. (eds.) CLEF 2016. LNCS, vol. 9822, pp. 28–39. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-44564-9_3CrossRefGoogle Scholar
  10. 10.
    Losada, D.E., Crestani, F., Parapar, J.: Overview of eRisk: early risk prediction on the internet. In: Bellot, P., et al. (eds.) CLEF 2018. LNCS, vol. 11018, pp. 343–361. Springer, Cham (2018).  https://doi.org/10.1007/978-3-319-98932-7_30CrossRefGoogle Scholar
  11. 11.
    Marchant, A., et al.: A systematic review of the relationship between internet use, self-harm and suicidal behaviour in young people: the good, the bad and the unknown. PLOS One 12(8), e0181722 (2017)CrossRefGoogle Scholar
  12. 12.
    Patchin, J.W., Hinduja, S.: Digital self-harm among adolescents. J. Adolesc. Health 61(6), 761–766 (2017)CrossRefGoogle Scholar
  13. 13.
    Pentina, A., Lampert, C.H.: Multi-task learning with labeled and unlabeled tasks. arXiv preprint arXiv:1602.06518 (2016)
  14. 14.
    Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 77(2), 257–286 (1989)CrossRefGoogle Scholar
  15. 15.
    Skegg, K.: Self-harm. Lancet 366(9495), 1471–1483 (2005)CrossRefGoogle Scholar
  16. 16.
    Tausczik, Y.R., Pennebaker, J.W.: The psychological meaning of words: LIWC and computerized text analysis methods. J. Lang. Soc. Psychol. 29(1), 24–54 (2010)CrossRefGoogle Scholar
  17. 17.
    Trotzek, M., Koitka, S., Friedrich, C.M.: Word embeddings and linguistic metadata at the CLEF 2018 tasks for early detection of depression and anorexia (2018). http://ceur-ws.org/Vol-2125/
  18. 18.
    Wang, T., Brede, M., Ianni, A., Mentzakis, E.: Detecting and characterizing eating-disorder communities on social media. In: Proceedings of the Tenth ACM International Conference on Web Search and Data Mining, pp. 91–100. ACM (2017)Google Scholar
  19. 19.
    Wang, Y., et al.: Understanding and discovering deliberate self-harm content in social media. In: Proceedings of the 26th International Conference on World Wide Web, pp. 93–102. International World Wide Web Conferences Steering Committee (2017)Google Scholar
  20. 20.
    Weiss, K., Khoshgoftaar, T.M., Wang, D.D.: A survey of transfer learning. J. Big Data 3, 9 (2016)CrossRefGoogle Scholar
  21. 21.
    Wolf, M., Theis, F., Kordy, H.: Language use in eating disorder blogs: psychological implications of social online activity. J. Lang. Soc. Psychol. 32(2), 212–226 (2013)CrossRefGoogle Scholar
  22. 22.
    Zdanow, C., Wright, B.: The representation of self injury and suicide on emo social networking groups. Afr. Sociol. Rev./Rev. Africaine de Sociologie 16(2), 81–101 (2012)Google Scholar
  23. 23.
    Zhang, Y., Yang, Q.: A survey on multi-task learning. CoRR abs/1707.08114 (2017)Google Scholar
  24. 24.
    Ziser, Y., Reichart, R.: Pivot Based Language Modeling for Improved Neural Domain Adaptation. NAACL Submission, pp. 1–10 (2018)Google Scholar
  25. 25.
    Zubiaga, A., Aker, A., Bontcheva, K., Liakata, M., Procter, R.: Detection and resolution of rumours in social media: a survey. ACM Comput. Surv. (CSUR) 51(2), 32 (2018)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Duisburg-Essen UniversityDuisburgGermany

Personalised recommendations