Abstract
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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Centre for Suicide Research and Prevention, The University of Hong Kong. https://csrp.hku.hk/statistics/. Accessed 30 Mar 2018
World Health Organization Webpage. http://www.who.int/mental_health/suicide-prevention/world_report_2014/en/. Accessed 30 Mar 2018
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)
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)
Chan, M., et al.: Engagement of vulnerable youths using internet platforms. PLoS ONE 12(12), e0189023 (2017)
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)
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)
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)
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)
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)
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)
Kotsiantis, S.B.: Supervised machine learning: a review of classification techniques. Emerg. Artif. Intell. Appl. Comput. Eng. 160, 3–24 (2007)
Estabrooks, A., Jo, T., Japkowicz, N.: A multiple resampling method for learning from imbalanced data sets. Comput. Intell. 20(1), 18–36 (2004)
Zhang, Z., Ye, Q., Li, Y.: Sentiment classification of Internet restaurant reviews written in Cantonese. Expert Syst. Appl. 38(6), 7674–7682 (2011)
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)
Lin, T.-Y., et al.: Focal loss for dense object detection. arXiv preprint arXiv:1708.02002 (2017)
Cheung, K.-H., Bauer, R.S.: The representation of Cantonese with Chinese characters. University of California, Project on Linguistic Analysis (2002)
LIHKG Webpage. https://lihkg.com/category/30. Accessed 30 Mar 2018
Sogou Webpage. https://pinyin.sogou.com/dict/search/search_list/%D4%C1%D3%EF/normal. Accessed 30 Mar 2018
Python Webpage. https://pypi.python.org/pypi/googletrans. Accessed 30 Mar 2018
Python Webpage. https://pypi.python.org/pypi/OpenCC. Accessed 30 Mar 2018
GitHub Webpage. https://github.com/BYVoid/OpenCC. Accessed 30 Mar 2018
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)
GitHub Webpage. https://github.com/fxsjy/jieba. Accessed 30 Mar 2018
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)
Joachims, T.: Text categorization with support vector machines: learning with many relevant features. In: European Conference on Machine Learning (1998)
Breiman, L.: Bagging predictors. Mach. Learn. 24(2), 123–140 (1996)
Liaw, A., Wiener, M.: Classification and regression by randomForest. R. News 2(3), 18–22 (2002)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Computat. 9(8), 1735–1780 (1997)
Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. Adv. Neural Inf. Process. Syst. (2015)
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)
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)
Kubat, M., Matwin, S.: Addressing the curse of imbalanced training sets: one-sided selection. ICML, Vol. 97 (1997)
Scikit-learn Webpage. http://scikit-learn.org/stable/. Accessed 30 Mar 2018
Gensim Webpage. https://radimrehurek.com/gensim/models/word2vec.html. Accessed 30 Mar 2018
Keras Webpage. https://keras.io/models/sequential/. Accessed 30 Mar 2018
Acknowledgements
The study was supported by Hong Kong General Research Fund (Ref No.: 17628916).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
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. https://doi.org/10.1007/978-3-030-02686-8_30
Download citation
DOI: https://doi.org/10.1007/978-3-030-02686-8_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-02685-1
Online ISBN: 978-3-030-02686-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)