Skip to main content

Detecting Comments Showing Risk for Suicide in YouTube

  • Conference paper
  • First Online:
Proceedings of the Future Technologies Conference (FTC) 2018 (FTC 2018)

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 880))

Included in the following conference series:


Natural language processing (NLP) with Cantonese, a mixture of Traditional Chinese, borrowed characters to represent spoken terms, and English, is largely under developed. To apply NLP to detect social media posts showing suicide risk, which is a rare event in regular population, is even more challenging. This paper tried different text mining methods to classify comments in Cantonese on YouTube whether they indicate suicidal risk. Based on word vector feature, classification algorithms such as SVM, AdaBoost, Random Forest, and LSTM are employed to detect the comments’ risk level. To address the imbalance issue of the data, both re-sampling and focal loss methods are used. Based on improvement on both data and algorithm level, the LSTM algorithm can achieve more satisfied testing classification results (84.3% and 84.5% g-mean, respectively). The study demonstrates the potential of automatically detected suicide risk in Cantonese social media posts.

Q. Cheng—Equal first author.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
USD 169.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 219.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others


  1. Centre for Suicide Research and Prevention, The University of Hong Kong. Accessed 30 Mar 2018

  2. World Health Organization Webpage. Accessed 30 Mar 2018

  3. Cheng, Q., Chen, F., Lee, E.S.T., Yip, P.S.F.: The role of media in preventing student suicides: a Hong Kong experience. J. Affect. Disord. 227, 643–648 (2018)

    Article  Google Scholar 

  4. Cheng, Q., Kwok, C.L., Zhu, T., Guan, L., Yip, P.S.F.: Suicide communication on social media and its psychological mechanisms: an examination of Chinese microblog users. Int. J. Environ. Res. Public Health 12(9), 11506–11527 (2015)

    Article  Google Scholar 

  5. Chan, M., et al.: Engagement of vulnerable youths using internet platforms. PLoS ONE 12(12), e0189023 (2017)

    Article  Google Scholar 

  6. Pestian, J.P., Matykiewicz, P., Grupp-Phelan, J.: Using natural language processing to classify suicide notes. In: Proceedings of the Workshop on Current Trends in Biomedical Natural Language Processing. Association for Computational Linguistics (2008)

    Google Scholar 

  7. Huang, Y.-P., Goh, T., Liew, C.L.: Hunting suicide notes in web 2.0-preliminary findings. In: Ninth IEEE International Symposium on Multimedia Workshops, ISMW 2007. IEEE (2007)

    Google Scholar 

  8. Moreno, M.A., et al.: Feeling bad on Facebook: depression disclosures by college students on a social networking site. Depress. Anxiety 28(6), 447–455 (2011)

    Article  Google Scholar 

  9. O’Dea, B., Wan, S., Batterham, P.J., Calear, A.L., Paris, C., Christensen, H.: Detecting suicidality on Twitter. Internet Interv. 2(2), 183–188 (2015)

    Article  Google Scholar 

  10. Vioulès, M.J., Moulahi, B., Azé, J., Bringay, S.: Detection of suicide-related posts in Twitter data streams. IBM J. Res. Dev. 62(1), 7:1–7:12 (2018)

    Article  Google Scholar 

  11. Cheng, Q., Li, T.M.H., Kwok, C.L., Zhu, T., Yip, P.S.F.: Assessing suicide risk and emotional distress in Chinese social media: a text mining and machine learning study. J. Med. Internet Res. 19(7), e243 (2017)

    Article  Google Scholar 

  12. Kotsiantis, S.B.: Supervised machine learning: a review of classification techniques. Emerg. Artif. Intell. Appl. Comput. Eng. 160, 3–24 (2007)

    MathSciNet  MATH  Google Scholar 

  13. Estabrooks, A., Jo, T., Japkowicz, N.: A multiple resampling method for learning from imbalanced data sets. Comput. Intell. 20(1), 18–36 (2004)

    Article  MathSciNet  Google Scholar 

  14. Zhang, Z., Ye, Q., Li, Y.: Sentiment classification of Internet restaurant reviews written in Cantonese. Expert Syst. Appl. 38(6), 7674–7682 (2011)

    Article  Google Scholar 

  15. Zhang, Z., Ye, Q., Li, Y., Law, R.: Sentiment classification of online Cantonese reviews by supervised machine learning approaches. Int. J. Web Eng. Technol. 5(4), 382–397 (2009)

    Article  Google Scholar 

  16. Lin, T.-Y., et al.: Focal loss for dense object detection. arXiv preprint arXiv:1708.02002 (2017)

  17. Cheung, K.-H., Bauer, R.S.: The representation of Cantonese with Chinese characters. University of California, Project on Linguistic Analysis (2002)

    Google Scholar 

  18. LIHKG Webpage. Accessed 30 Mar 2018

  19. Sogou Webpage. Accessed 30 Mar 2018

  20. Python Webpage. Accessed 30 Mar 2018

  21. Python Webpage. Accessed 30 Mar 2018

  22. GitHub Webpage. Accessed 30 Mar 2018

  23. Zou, F., Wang, F.L., Deng, X., Han, S., Wang, L.S.: Automatic construction of Chinese stop word list. In: Proceedings of the 5th WSEAS International Conference on Applied Computer Science (2006)

    Google Scholar 

  24. GitHub Webpage. Accessed 30 Mar 2018

  25. Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. Adv. Neural Inf. Process. Syst. (2013)

    Google Scholar 

  26. Joachims, T.: Text categorization with support vector machines: learning with many relevant features. In: European Conference on Machine Learning (1998)

    Google Scholar 

  27. Breiman, L.: Bagging predictors. Mach. Learn. 24(2), 123–140 (1996)

    MathSciNet  MATH  Google Scholar 

  28. Liaw, A., Wiener, M.: Classification and regression by randomForest. R. News 2(3), 18–22 (2002)

    Google Scholar 

  29. Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Computat. 9(8), 1735–1780 (1997)

    Article  Google Scholar 

  30. Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. Adv. Neural Inf. Process. Syst. (2015)

    Google Scholar 

  31. Kim, S.-M., Hovy, E.: Determining the sentiment of opinions. In: Proceedings of the 20th International Conference on Computational Linguistics. Association for Computational Linguistics (2004)

    Google Scholar 

  32. Liu, X.-Y., Wu, J., Zhou, Z.-H.: Exploratory undersampling for class-imbalance learning. IEEE Trans. Syst. Man Cybern. Part B (Cybern.) 39(2), 539–550 (2009)

    Article  Google Scholar 

  33. Kubat, M., Matwin, S.: Addressing the curse of imbalanced training sets: one-sided selection. ICML, Vol. 97 (1997)

    Google Scholar 

  34. Scikit-learn Webpage. Accessed 30 Mar 2018

  35. Gensim Webpage. Accessed 30 Mar 2018

  36. Keras Webpage. Accessed 30 Mar 2018

Download references


The study was supported by Hong Kong General Research Fund (Ref No.: 17628916).

Author information

Authors and Affiliations


Corresponding author

Correspondence to Qijin Cheng .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Gao, J., Cheng, Q., Yu, P.L.H. (2019). Detecting Comments Showing Risk for Suicide in YouTube. In: Arai, K., Bhatia, R., Kapoor, S. (eds) Proceedings of the Future Technologies Conference (FTC) 2018. FTC 2018. Advances in Intelligent Systems and Computing, vol 880. Springer, Cham.

Download citation

Publish with us

Policies and ethics