Detecting Depression in Social Media Posts Using Machine Learning

  • Abhilash BiradarEmail author
  • S. G. Totad
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1037)


The utilization of Social Networking Sites (SNS) like Twitter is expanding quickly and particularly by the more youthful age. The profit capacity of SNS enables us to express their interests, emotions and offer their day by day schedule. SNS sites such as Twitter allow for constant investigation of user behaviour. Such examples are important for the psychological research network to comprehend the periods and area of most prominent interest. Worlds fourth biggest disease depression has turned out to be a standout amongst the most huge research subject. We propose a system which uses tweets as source of data and SentiStrength sentiment analysis to create a training data for our system and a Back Propagation Neural Network (BPNN) model to classify the given tweets into depressed or not depressed categories.


Back Propagation Neural Network (BPNN) Depression Machine learning Social Network Sites (SNS) SentiStrength Twitter 


  1. 1.
    Duggan, M., Ellison, N.B., Lampe, C., Madden, M.: Social Media Update 2014. Pew Research Center (2015)Google Scholar
  2. 2.
    Ramirez-Esparza, N., Chung, C.K., Kacewicz, E., Pennebaker, J.W.: The psychology of word use in depression forums in English and in Spanish: testing two text analytic approaches. In: Proceedings of the International Conference on Weblogs and Social Media, pp. 102–108. AAAI Press, Menlo Park (2008)Google Scholar
  3. 3.
    Moreno, M.A., et al.: Feeling bad on Facebook: depression disclosures by college students on social networking site. Depression Anxiety 28(6), 447–455 (2011)CrossRefGoogle Scholar
  4. 4.
    Numbers of monthly active Twitter users in 4th Quarter 2017 — Statistic (2017). Accessed 21 Jan 2018
  5. 5.
    Jalonen, H.: An arena for venting negative emotions. In: International Conference on Communication, Media, Technology and Design, Istanbul, Turkey, pp. 224–230 (2014)Google Scholar
  6. 6.
    Aldarwish, M.M., Ahmed, H.F.: Predicting depression levels using social media posts. In: 2017 IEEE 13th International Symposium on Autonomous Decentralized Systems (2017)Google Scholar
  7. 7.
    Hussain, J., et al.: SNS based predictive model for depression. In: Geissbühler, A., Demongeot, J., Mokhtari, M., Abdulrazak, B., Aloulou, H. (eds.) ICOST 2015. LNCS, vol. 9102, pp. 349–354. Springer, Cham (2015). Scholar
  8. 8.
    Java, A., Song, X., Finin, T., Tseng, B.: Why we Twitter: understanding microblogging usage and communities. In: Proceedings of the 9th WebKDD and 1st SNA-KDD 2007 Workshop on Web Mining and Social Network Analysis, pp. 56–65. ACM Press, New York (2007)Google Scholar
  9. 9.
    Naaman, M., Boase, J., Lai, C.-H.: Is it really about me? Message content in social awareness streams. In: Proceedings of the 2010 ACM Conference on Computer Supported Cooperative Work. ACM Press, New York (2010)Google Scholar
  10. 10.
    Thelwall, M., Buckley, K., Paltoglou, G., Cai, D., Kappas, A.: Sentiment strength detection in short informal text. J. Am. Soc. Inform. Sci. Technol. 61(12), 2544–2558 (2010)CrossRefGoogle Scholar
  11. 11.
    Frances, A., Pincus, H., First, M.: Major depressive episode. In: The Diagnostic and Statistical Manual of Mental Disorders: DSM-IV, 4th edn., pp. 326–327. American Psychiatric Association, Washington, D.C. (1994)Google Scholar
  12. 12.
    Pang, J., Bu, D., Bai, S.: Research and implementation of text categorization system based on VSM. Appl. Res. Comput. 9, 23–26 (2003)Google Scholar
  13. 13.
    Wang, Z., He, Y., Jiang, M.: A comparison among three Neural Network for text classification. In: Proceedings of the 2006 International Conference on Signal Processing (2006)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Department of Computer ScienceB.V.B College of EngineeringHubliIndia

Personalised recommendations