自殺是一個全球性的死亡主因，許多研究都嘗試以早期偵測的角度來切入自殺防治。找出潛在的自殺者是個重要但困難的任務，本研究嘗試使用近幾年快速發展的深度學習自然語言處理技術來建立自殺風險預測模型，以及偵測語句中兩類自殺相關訊息，包含「表達自殺意念／自殺企圖」和「含有自殺方式」。
研究資料使用866個安心專線的通話錄音檔，將錄音檔騰打為逐字稿後進行文字處理和分析。在建立安心專線來電者的自殺風險預測模型上，使用了Sentence-BERT的語意相似度與兩個自殺量表題目比對，篩選出有助於預測的句子，並進一步透過Sentence-BERT對句子進行特徵提取以建立分類模型。此外，本研究嘗試透過人工標註的方式提供句子層級的自殺相關訊息，人工標註的結果會用於建立句子層級的自殺相關訊息預測模型，微調BERT以及兩類機器學習模型將被用於訓練此類模型。最後，本研究會檢驗標註的自殺相關訊息對於預測自殺風險的增益效果。
研究結果顯示，使用Sentence-BERT提取的句子嵌入資訊能夠有效預測自殺風險，結合主成分分析與隨機森林之分類正確率達到83.9%。而在偵測語句中自殺相關訊息的任務上，微調BERT訓練的模型表現優於另外兩類使用句子嵌入資訊的機器學習模型，在「表達自殺意念／自殺企圖」與「含有自殺方式」的分類正確率分別為95.8%、99.1%。最後，本研究使用的兩類自殺相關訊息對於預測自殺風險並沒有額外的增益效果。

Suicide is a leading cause of death in the globe, and many studies underscore early detection in suicide prevention. However, it is a difficult task to identify suicide attempters. The present research employs the natural language processing techniques based on deep learning to build the model for suicide risk prediction and detecting suicide-related information, including “expression of suicidal ideation/suicide attempt” and “mentioning of suicide method.”
In this paper, 866 speech recordings from the Lifeline were transcribed and analyzed. These recordings were used to build a suicide risk prediction model. The model used Sentence-BERT to compare the semantic similarity between the recordings and two suicide scales in order to identify sentences high in predictive power. Furthermore, Sentence-BERT was again used to feature extraction on these sentences in order to build a classification model. In addition, to provide suicide-related information on the sentence level, this paper used manual coding for the recordings. These manual coding were used to build model on the sentence-level and fine tune the BERT model. Finally, the paper examined the incremental predictive effect of model-classified suicide-related information on predicting suicide risk.
Results showed that information of sentence embedding from Sentence-Bert was able to effectively predict suicide risks. The accuracy of random forest combined with principal component analysis was to 83.9%. For detection of suicide-related information, the fine-tuned BERT model was better than the other two machine-learning models. The accuracy of suicidal ideation/suicide attempt and suicide method is 95.8% and 99.1%, respectively. Finally, the paper did not find incremental predictive effect on predicting two kinds of suicide-related information to predict suicide risks.

張壽山（2000）：《貝克自殺意念量表（BHS）中文版》。中國行為科學社。[Zhang, S.-S. (2000). The Chinese version of Beck scale for suicide ideation. Chinese Behavioral Science Corporation.]
許文耀、鍾瑞玫（1997）：〈「自殺危險程度量表」的編製及其信、效度考驗〉。《中華心理衛生期刊》，10（2），1–17。[Hsu, W.-Y., & Chung, J.-M.(1997). Constructing a scale of suicidal risk and testing its reliability and validity. Formosa Journal of Mental Health, 10(2), 1–17.]
陳映燁、呂宗學、李馨如、郭千哲、邱震寰、陳喬琪（2006）：〈臺灣與南韓方 法別自殺率之比較〉。《北市醫學雜誌》，3，982–991。[Chen, Y.-Y., Lu, T.-H., Lee, H.-J., Kuo, C.-J., Chiu. C.-H., & Chen, C.-C. (2006). Comparison of ethod-specific suicide rates between Taiwan and South Korea. Taipei City Medical Journal, 3, 982–991.]https://doi.org/10.6200/TCMJ.2006.3.10.04
陳美君（2000）：《貝克絕望感量表（BHS）中文版》。中國行為科學社。[Chen, M.-J. (2000). The Chinese version of Beck hopelessness scale. Chinese Behavioral Science Corporation.]
衛生福利部（2021）：〈110年死因統計結果摘要〉。https://dep.mohw.gov.tw/DOS/lp-5069-113-xCat-y110.html [Ministry of Health and Welfare. (2021). 110 nian siyin tongji zhaiyao.https://dep.mohw.gov.tw/DOS/lp-5069-113-xCat-y110.html]
Ahmedani, B. K., Simon, G. E., Stewart, C., Beck, A., Waitzfelder, B. E., Rossom, R., Lynch, F., Owen-Smith, A., Hunkeler, E. M., Whiteside, U., Operskalski, B. H., Coffey, M. J., & Solberg, L. I. (2014). Health care contacts in the year before suicide death. Journal of General Internal Medicine, 29, 870–877. https://doi.org/10.1007/s11606-014-2767-3
Almeida, F., & Xexéo, G. (2019). Word embeddings: A survey. arXiv preprint arXiv:1901.09069. https://doi.org/10.48550/arXiv.1901.09069
Alyafeai, Z., AlShaibani, M. S., & Ahmad, I. (2020). A survey on transfer learning in natural language processing. arXiv preprint arXiv:2007.04239.https://doi.org/10.48550/arXiv.2007.04239
Arya, V., Page, A., Gunnell, D., Dandona, R., Mannan, H., Eddleston, M., & Armstrong, G. (2019). Suicide by hanging is a priority for suicide prevention: Method specific suicide in India (2001-2014). Journal of Affective Disorders, 257, 1–9. https://doi.org/10.1016/j.jad.2019.07.005
Beck, A. T., Steer, R. A., & Ranieri, W. F. (1988). Scale for suicide ideation: Psychometric properties of a self‐report version. Journal of Clinical Psychology, 44, 499–505. https://doi.org/10.1002/1097-4679(198807)44:4<499::AID-JCLP2270440404>3.0.CO;2-6
Beck, A. T., Weissman, A., Lester, D., & Trexler, L. (1974). The measurement of pessimism: The hopelessness scale. Journal of Consulting and Clinical Psychology, 42, 861–865. https://doi.org/10.1037/h0037562
Bengio, Y., Courville, A., & Vincent, P. (2013). Representation learning: A review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35, 1798–1828. https://doi.org/10.1109/tpami.2013.50
Bengio, Y., Ducharme, R., Vincent, P., & Jauvin, C. (2003). A neural probabilistic language model. Journal of Machine Learning Research, 3, 1137–1155.
Bentley, K. H., Franklin, J. C., Ribeiro, J. D., Kleiman, E. M., Fox, K. R., & Nock, M. K. (2016). Anxiety and its disorders as risk factors for suicidal thoughts and behaviors: A meta-analytic review. Clinical Psychology Review, 43, 30–46. https://doi.org/10.1016/j.cpr.2015.11.008
Bhat, H. S., & Goldman-Mellor, S. J. (2017). Predicting adolescent suicide attempts with neural networks. arXiv preprint arXiv:1711.10057.https://doi.org/10.48550/arXiv.1711.10057
Birjali, M., Beni-Hssane, A., & Erritali, M. (2017). Machine learning and semantic sentiment analysis based algorithms for suicide sentiment prediction in social networks. Procedia Computer Science, 113, 65–72. https://doi.org/10.1016/j.procs.2017.08.290
Bostwick, J. M., Pabbati, C., Geske, J. R., & McKean, A. J. (2016). Suicide attempt as a risk factor for completed suicide: Even more lethal than we knew. American Journal of Psychiatry, 173, 1094–1100. https://doi.org/10.1176/appi.ajp.2016.15070854
Capron, D. W., Fitch, K., Medley, A., Blagg, C., Mallott, M., & Joiner, T. (2012). Role of anxiety sensitivity subfactors in suicidal ideation and suicide attempt history. Depression and Anxiety, 29, 195–201.https://doi.org/10.1002/da.20871
Card, J. J. (1974). Lethality of suicidal methods and suicide risk: Two distinct concepts. Omega-journal of Death and Dying, 5, 37–45. https://doi.org/10.2190/K59M-Y0KN-PAKV-JFUV
Castillo-Sánchez, G., Marques, G., Dorronzoro, E., Rivera-Romero, O., Franco-Martín, M., & De La Torre-Díez, I. (2020). Suicide risk assessment using machine learning and social networks: A scoping review. Journal of Medical Systems, 44(12), 1–15. https://doi.org/10.1007/s10916-020-01669-5
Chang, E. C. (2017). Hope and hopelessness as predictors of suicide ideation in Hungarian college students. Death Studies, 41, 455–460. https://doi.org/10.1080/07481187.2017.1299255
Chowdhary, K. (2020). Fundamentals of artificial intelligence. Springer. https://doi.org/10.1007/978-81-322-3972-7
Cohen, J. (1960). A coefficient of agreement for nominal scales. Educational and Psychological Measurement, 20, 37–46. https://doi.org/10.1177/001316446002000104
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805. https://doi.org/10.48550/arXiv.1810.04805
Du, J., Zhang, Y., Luo, J., Jia, Y., Wei, Q., Tao, C., & Xu, H. (2018). Extracting psychiatric stressors for suicide from social media using deep learning. BMC Medical Informatics and Decision Making, 18(2), 77–87. https://doi.org/10.1186/s12911-018-0632-8
Dutta, R., Ball, H., Siribaddana, S., Sumathipala, A., Samaraweera, S., McGuffin, P., & Hotopf, M. (2017). Genetic and other risk factors for suicidal ideation and the relationship with depression. Psychological Medicine, 47, 2438–2449. https://doi.org/10.1017/S0033291717000940
Géron, A. (2019). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems. O'Reilly Media.
Grant, R. N., Kucher, D., León, A. M., Gemmell, J. F., Raicu, D. S., & Fodeh, S. J. (2018). Automatic extraction of informal topics from online suicidal ideation. BMC Bioinformatics, 19(8), 57–66.https://doi.org/10.1186/s12859-018-2197-z
Gunnell, D., Middleton, N., & Frankel, S. (2000). Method availability and the prevention of suicide - a re-analysis of secular trends in England and Wales 1950-1975. Social Psychiatry and Psychiatric Epidemiology, 35, 437–443. https://doi.org/10.1007/s001270050261
Han, B., Compton, W. M., Gfroerer, J., & McKeon, R. (2015). Prevalence and correlates of past 12-month suicide attempt among adults with past-year suicidal ideation in the United States. The Journal of Clinical Psychiatry, 76, 295–302. https://doi.org/10.4088/JCP.14m09287
Harris, Z. S. (1954). Distributional structure. Word, 10(2-3), 146–162. https://doi.org/10.1080/00437956.1954.11659520
Horwitz, A. G., Berona, J., Czyz, E. K., Yeguez, C. E., & King, C. A. (2017). Positive and negative expectations of hopelessness as longitudinal predictors of depression, suicidal ideation, and suicidal behavior in high-risk adolescents. Suicide and Life-Threatening Behavior, 47(2), 168–176. https://doi.org/10.1111/sltb.12273
Hu, J., Dong, Y., Chen, X., Liu, Y., Ma, D., Liu, X., Zheng, R., Mao, X., Chen, T., & He, W. (2015). Prevalence of suicide attempts among Chinese adolescents: A meta-analysis of cross-sectional studies. Comprehensive Psychiatry, 61, 78–89. https://doi.org/10.1016/j.comppsych.2015.05.001
Hubers, A., Moaddine, S., Peersmann, S., Stijnen, T., Van Duijn, E., Van der Mast, R., Dekkers, O., & Giltay, E. (2018). Suicidal ideation and subsequent completed suicide in both psychiatric and non-psychiatric populations: A meta-analysis. Epidemiology and Psychiatric Sciences, 27, 186–198. https://doi.org/10.1017/S2045796016001049
Joiner , T. E., Jr., Conwell, Y., Fitzpatrick, K. K., Witte, T. K., Schmidt, N. B., Berlim, M. T., Fleck, M., & Rudd, M. D. (2005). Four studies on how past and current suicidality relate even when “everything but the kitchen sink” is covaried. Journal of Abnormal Psychology, 114, 291–303. https://doi.org/10.1037/0021-843X.114.2.291
Jollant, F., Hawton, K., Vaiva, G., Chan-Chee, C., du Roscoat, E., & Leon, C. (2022). Non-presentation at hospital following a suicide attempt: A national survey. Psychological Medicine, 52, 707–714. https://doi.org/10.1017/S0033291720002305
Kandel, D. B., Raveis, V. H., & Davies, M. (1991). Suicidal ideation in adolescence: Depression, substance use, and other risk factors. Journal of Youth and Adolescence, 20, 289–309. https://doi.org/10.1007/BF01537613
Kim, H., Kim, Y., Lee, G., Choi, J. H., Yook, V., Shin, M.-H., & Jeon, H. J. (2021). Predictive factors associated with methods of suicide: The Korean national investigations of suicide victims (the KNIGHTS study). Frontiers in Psychiatry, 12, 1–13. https://doi.org/10.3389/fpsyt.2021.651327
Labach, A., Salehinejad, H., & Valaee, S. (2019). Survey of dropout methods for deep neural networks. arXiv preprint arXiv:1904.13310.https://doi.org/10.48550/arXiv.1904.13310
Lecun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521, 436–444. https://doi.org/10.1038/nature14539
Leiva, V., & Freire, A. (2017). Towards suicide prevention: Early detection of depression on social media. In I. Kompatsiaris, J. Cave, A. Satsiou, G. Carle & A. Passani (Eds.), Internet science (pp. 428–436). Springer. https://doi.org/10.1007/978-3-319-70284-1_34
Leshno, M., Lin, V. Y., Pinkus, A., & Schocken, S. (1993). Multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural Networks, 6, 861–867. https://doi.org/10.1016/S0893-6080(05)80131-5
Lester, D. (2008). Suicide and culture. World Cult Psychiatry Res Rev (WCPRR), 3(2), 51–68.
Li, H. (2017). Deep learning for natural language processing: Advantages and challenges. National Science Review, 5, 24–26. https://doi.org/10.1093/nsr/nwx110
Li, Z.-Z., Li, Y.-M., Lei, X.-Y., Zhang, D., Liu, L., Tang, S.-Y., & Chen, L. (2014). Prevalence of suicidal ideation in Chinese college students: A meta-analysis. PLoS One, 9(10), 1–12. https://doi.org/10.1371/journal.pone.0104368
Lim, M., Lee, S. U., & Park, J.-I. (2014). Difference in suicide methods used between suicide attempters and suicide completers. International Journal of Mental Health Systems, 8(1), 1–4. https://doi.org/10.1186/1752-4458-8-54
Lin, J.-J., & Lu, T.-H. (2006). Association between the accessibility to lethal methods and method-specific suicide rates: An ecological study in Taiwan. Journal of Clinical Psychiatry, 67, 1074–1079. https://doi.org/1074-1079.10.4088/jcp.v67n0709
Liu, H., Zhang, R., Liu, Y., & He, C. (2022). Unveiling evolutionary path of nanogenerator technology: A novel method based on Sentence-BERT. Nanomaterials, 12(12), 1–14. https://doi.org/10.3390/nano12122018
Luxton, D. D., June, J. D., & Fairall, J. M. (2012). Social media and suicide: A public health perspective. American Journal of Public Health, 102(S2), S195–S200. https://doi.org/10.2105/AJPH.2011.300608
Marzuk, P. M., Leon, A. C., Tardiff, K., Morgan, E. B., Stajic, M., & Mann, J. J. (1992). The effect of access to lethal methods of injury on suicide rates. Archives of General Psychiatry, 49, 451–458. https://doi.org/10.1001/archpsyc.1992.01820060031005
Masango, S., Rataemane, S., & Motojesi, A. (2008). Suicide and suicide risk factors: A literature review. South African Family Practice, 50(6), 25–29. https://doi.org/10.1080/20786204.2008.10873774
Matero, M., Idnani, A., Son, Y., Giorgi, S., Vu, H., Zamani, M., Limbachiya, P., Guntuku, S. C., & Schwartz, H. A. (2019 , June). Suicide risk assessment with multi-level dual-context language and BERT [symposium presentation]. The Sixth Workshop on Computational Linguistics and Clinical Psychology, Minneapolis, Minnesota. https://doi.org/10.18653/v1/W19-3005
McHugh, M. L. (2012). Interrater reliability: The kappa statistic. Biochemia Medica, 22, 276–282. https://doi.org/10.11613/BM.2012.031
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781. https://doi.org/10.48550/arXiv.1301.3781
Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. arXiv preprint arXiv:1310.4546. https://doi.org/10.48550/arXiv.1310.4546
Nair, V., & Hinton, G. E. (2010, June). Rectified linear units improve restricted boltzmann machines [symposium presentation]. The 27th international conference on machine learning, Haifa, Israel.
O Carroll, P. W., Berman, A. L., Maris, R. W., Moscicki, E. K., Tanney, B. L., & Silverman, M. M. (1996). Beyond the tower of babel: A nomenclature for suicidology. Suicide & Life - Threatening Behavior, 26, 237–252. https://doi.org/10.1111/j.1943-278X.1996.tb00609.x
Olfson, M., Wall, M., Wang, S., Crystal, S., Gerhard, T., & Blanco, C. (2017). Suicide following deliberate self-harm. American Journal of Psychiatry, 174, 765–774. https://doi.org/10.1176/appi.ajp.2017.16111288
Ophir, Y., Tikochinski, R., Asterhan, C. S. C., Sisso, I., & Reichart, R. (2020). Deep neural networks detect suicide risk from textual facebook posts. Scientific Reports, 10, 1–10. https://doi.org/10.1038/s41598-020-73917-0
Otter, D. W., Medina, J. R., & Kalita, J. K. (2021). A survey of the usages of deep Learning for Natural Language Processing. IEEE Transactions on Neural Networks and Learning Systems, 32, 604–624. https://doi.org/10.1109/tnnls.2020.2979670
Pan, S. J., & Yang, Q. (2009). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22, 1345–1359. https://doi.org/10.1186/s40537-016-0043-6
Parraga-Alava, J., Caicedo, R. A., Gómez, J. M., & Inostroza-Ponta, M. (2019). An unsupervised learning approach for automatically to categorize potential suicide messages in social media [symposium presentation]. 2019 38th international conference of the chilean computer science society (SCCC), Concepcion, Chile. https://doi.org/10.1109/SCCC49216.2019.8966443
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., & Dubourg, V. (2011). Scikit-learn: Machine learning in Python. The Journal of Machine Learning Research, 12, 2825–2830.
Posner, K., Oquendo, M. A., Gould, M., Stanley, B., & Davies, M. (2007). Columbia Classification Algorithm of Suicide Assessment (C-CASA): Classification of suicidal events in the FDA’s pediatric suicidal risk analysis of antidepressants. American Journal of Psychiatry, 164, 1035–1043. https://doi.org/10.1176/appi.ajp.164.7.1035
Probert-Lindström, S., Berge, J., Westrin, Å., Öjehagen, A., & Pavulans, K. S. (2020). Long-term risk factors for suicide in suicide attempters examined at a medical emergency in patient unit: Results from a 32-year follow-up study. BMJ Open, 10(10), 1–10. https://doi.org/10.1136/bmjopen-2020-03879
Qiu, T., Klonsky, E. D., & Klein, D. N. (2017). Hopelessness predicts suicide ideation but not attempts: A 10‐year longitudinal study. Suicide and Life‐Threatening Behavior, 47, 718–722. https://doi.org/10.1111/sltb.12328
Qiu, X., Sun, T., Xu, Y., Shao, Y., Dai, N., & Huang, X. (2020). Pre-trained models for natural language processing: A survey. Science China Technological Sciences, 63, 1872–1897. https://doi.org/10.1007/s11431-020-1647-3
Rath, S., & Chow, J. Y. (2022). Worldwide city transport typology prediction with sentence-BERT based supervised learning via Wikipedia. Transportation Research Part C: Emerging Technologies, 139, 1–31. https://doi.org/10.1016/j.trc.2022.103661
Reimers, N., & Gurevych, I. (2019). Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084.https://doi.org/10.48550/arXiv.1908.10084
Rossom, R. C., Coleman, K. J., Ahmedani, B. K., Beck, A., Johnson, E., Oliver, M., & Simon, G. E. (2017). Suicidal ideation reported on the PHQ9 and risk of suicidal behavior across age groups. Journal of Affective Disorders, 215, 77–84. https://doi.org/10.1016/j.jad.2017.03.037
Schulz, R., Drayer, R. A., & Rollman, B. L. (2002). Depression as a risk factor for non-suicide mortality in the elderly. Biological Psychiatry, 52, 205–225. https://doi.org/10.1016/S0006-3223(02)01423-3
Shelef, L., Rabbany, J. M., Gutierrez, P. M., Kedem, R., Ben Yehuda, A., Mann, J. J., & Yacobi, A. (2021). The role of past suicidal behavior on current suicidality: A retrospective study in the Israeli Military. International Journal of Environmental Research and Public Health, 18(2), 1–14. https://doi.org/10.3390/ijerph18020649
Simon, G. E., Johnson, E., Lawrence, J. M., Rossom, R. C., Ahmedani, B., Lynch, F. L., Beck, A., Waitzfelder, B., Ziebell, R., Penfold, R. B., & Shortreed, S. M. (2018). Predicting suicide attempts and suicide deaths following outpatient visits using electronic health records. American Journal of Psychiatry, 175, 951–960. https://doi.org/10.1176/appi.ajp.2018.17101167
Spicer, R. S., & Miller, T. R. (2000). Suicide acts in 8 states: Incidence and case fatality rates by demographics and method. American Journal of Public Health, 90, 1885–1891. https://doi.org/10.2105/ajph.90.12.1885
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, 15(1), 1929–1958.
Stanley, I. H., Boffa, J. W., Rogers, M. L., Hom, M. A., Albanese, B. J., Chu, C., Capron, D. W., Schmidt, N. B., & Joiner, T. E. (2018). Anxiety sensitivity and suicidal ideation/suicide risk: A meta-analysis. Journal of Consulting and Clinical Psychology, 86, 946–960. https://doi.org/10.1037/ccp0000342
Sumarokov, Y. A., Brenn, T., Kudryavtsev, A. V., & Nilssen, O. (2015). Variations in suicide method and in suicide occurrence by season and day of the week in Russia and the Nenets Autonomous Okrug, Northwestern Russia: A retrospective population-based mortality study. BMC Psychiatry, 15, 1–9. https://doi.org/10.1186/s12888-015-0601-z
Tadesse, M. M., Lin, H., Xu, B., & Yang, L. (2019). Detection of suicide ideation in social media forums using deep learning. Algorithms, 13(1), 1–19. https://doi.org/10.3390/a13010007
Van Heeringen, C. (2001). Understanding suicidal behaviour: The suicidal process approach to research, treatment and prevention. Wiley.
Wang, N., Luo, F., Shivtare, Y., Badal, V. D., Subbalakshmi, K., Chandramouli, R., & Lee, E. (2021). Learning models for suicide prediction from social media posts. arXiv preprint arXiv:2105.03315.https://doi.org/10.48550/arXiv.2105.03315
World Health Organization. (2021).Suicide worldwide in 2019: Global health estimates. World Health Organization.
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., & Funtowicz, M. (2020). Transformers: State-of-the-art natural language processing [symposium presentation]. 2020 conference on empirical methods in natural language processing: system demonstrations. https://doi.org/10.18653/v1/2020.emnlp-demos.6
Wongkoblap, A., Vadillo, M. A., & Curcin, V. (2017). Researching mental health disorders in the era of social media: Systematic review. Journal of Medical Internet Research, 19(6), 1–17. https://doi.org/10.2196/jmir.7215
Wu, K. C.-C., Chen, Y.-Y., & Yip, P. S. (2012). Suicide methods in Asia: Implications in suicide prevention. International Journal of Environmental Research and Public Health, 9, 1135–1158. https://doi.org/10.3390/ijerph9041135
Zhang, L., Huang, X., Liu, T., Li, A., Chen, Z., & Zhu, T. (2014). Using linguistic features to estimate suicide probability of Chinese microblog users. In Q. Zu, B. Hu, N. Gu & S. Seng (Eds.), Human centered computing (pp. 549–559). Springer. https://doi.org/10.48550/arXiv.1411.0861