Skip to main content

Advertisement

SpringerLink
Log in

Stacked CNN - LSTM approach for prediction of suicidal ideation on social media

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

The growing use of social media forums to express suicidal ideation creates an immense requirement for automatic recognition of suicidal posts. Individuals use social forums to discuss their problems or access information on similar topics. This study aims to work on the automatic recognition and flagging of suicidal posts. It presents an approach that analyses social media platform Twitter to identify suicide warning signs for individuals. The primary purpose of the mentioned approach is the automatic identification of abnormal changes in online behaviour of the user. The challenges faced in suicide prevention is the understanding and detection of complex risk factors or warning signs that may lead to the event. To achieve this task, numerous natural language processing (NLP) techniques are employed to quantify linguistic and textual changes and pass through a novel framework which can be applied at large. The preliminary detection of suicidal ideation is achieved through deep learning and machine learning-based classification models applied to tweets on Twitter social media. For both classifiers initially we executed data pre-processing, feature extraction subsequently machine learning and deep learning classifiers respectively. For this purpose, we employ a Stacked CNN - 2 Layer LSTM model to evaluate and compare with other classification models. The study shows that the Stacked CNN - 2 Layer LSTM architecture with word embedding techniques achieves 93.92% classification accuracy as compared to previous previous CNN - LSTM approaches.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  1. Ahmad S, Asghar MZ, Alotaibi FM, Awan I (2019) Detection and classification of social media-based extremist affiliations using sentiment analysis techniques. Human-centric Comput Inform Sci 9(1):24

    Article  Google Scholar 

  2. Basu T, Murthy CA (2012) A feature selection method for improved document classification. In international conference on advanced data mining and applications (pp. 296-305). Springer, Berlin, Heidelberg

  3. Beck AT, Kovacs M, Weissman A (1975) Hopelessness and suicidal behavior: an overview. Jama 234(11):1146–1149

    Article  Google Scholar 

  4. Bhat, H. S., & Goldman-Mellor, S. J. (2017) Predicting adolescent suicide attempts with neural networks. arXiv preprint arXiv:1711.10057

  5. Bird S, Klein E, Loper E (2009) Natural language processing with Python: analyzing text with the natural language toolkit. " O'Reilly Media, Inc."

  6. Chadha A, Kaushik B (2019) "A survey on prediction of suicidal ideation using machine and ensemble learning." Comput J

  7. Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. In proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794).

  8. Choi SB, Lee W, Yoon JH, Won JU, Kim DW (2018) Ten-year prediction of suicide death using cox regression and machine learning in a nationwide retrospective cohort study in South Korea. J Affect Disord 231:8–14

    Article  Google Scholar 

  9. Collobert R, Weston J (2008) A unified architecture for natural language processing: deep neural networks with multitask learning. In proceedings of the 25th international conference on machine learning (pp. 160-167)

  10. Dahl GE, Sainath TN, Hinton GE (2013) Improving deep neural networks for LVCSR using rectified linear units and dropout. In 2013 IEEE international conference on acoustics, speech and signal processing (pp. 8609-8613). IEEE

  11. De Choudhury M, Kiciman E, Dredze M, Coppersmith G, Kumar M (2016) Discovering shifts to suicidal ideation from mental health content in social media. In proceedings of the 2016 CHI conference on human factors in computing systems (pp. 2098-2110)

  12. 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 Med Informa Decis Making 18(2):77–87

    Google Scholar 

  13. Freund Y, Schapire R, Abe N (1999) A short introduction to boosting. J-Japan Soc Artificial Intel 14(771–780):1612

    Google Scholar 

  14. Gehrmann S, Dernoncourt F, Li Y, Carlson ET, Wu JT, Welt J, Foote J, Moseley ET, Grant DW, Tyler PD, Celi LA (2018) Comparing deep learning and concept extraction based methods for patient phenotyping from clinical narratives. PLoS One 13(2):e0192360

    Article  Google Scholar 

  15. Github. https://github.com/laxmimerit/twitter-suicidal-intention-dataset

  16. Goodfellow I, Bengio Y, Courville A, Bengio Y (2016) Deep learning (Vol. 1, no. 2). MIT press, Cambridge

    MATH  Google Scholar 

  17. Gupta S, Dinesh DA (2017) Resource usage prediction of cloud workloads using deep bidirectional long short term memory networks. In 2017 IEEE international conference on advanced networks and telecommunications systems (ANTS) (pp. 1-6). IEEE

  18. He H, Lin J (2016) Pairwise word interaction modeling with deep neural networks for semantic similarity measurement. In proceedings of the 2016 conference of the north American chapter of the Association for Computational Linguistics: human language technologies (pp. 937-948)

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

    Article  Google Scholar 

  20. Ji S, Yu CP, Fung SF, Pan S, Long G (2018) Supervised learning for suicidal ideation detection in online user content Complexity, 2018

  21. Ji S, Long G, Pan S, Zhu T, Jiang J, Wang S (2019) Detecting suicidal ideation with data protection in online communities. In international conference on database systems for advanced applications (pp. 225-229). Springer, Cham

  22. Kalchbrenner N, Grefenstette E, Blunsom P (2014) A convolutional neural network for modelling sentences. arXiv preprint arXiv:1404.2188

  23. Klonsky ED, May AM (2014) Differentiating suicide attempters from suicide ideators: a critical frontier for suicidology research. Suicide Life Threat Behav 44(1):1–5

    Article  Google Scholar 

  24. LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324

    Article  Google Scholar 

  25. Li J, Zhang S, Zhang Y, Lin H, Wang J (2021) Multifeature fusion attention network for suicide risk assessment based on social media: algorithm development and validation. JMIR Med Inform 9(7):e28227

    Article  Google Scholar 

  26. Lin G-M, Nagamine M, Yang S-N, Tai Y-M, Lin C, Sato H (2020) Machine learning based suicide ideation prediction for military personnel. IEEE J Biomed HealthIinform 24(7):1907–1916

    Article  Google Scholar 

  27. Marks, M. (2019). Artificial intelligence based suicide prediction

    Google Scholar 

  28. Mikolov T, Karafiát M, Burget L, Černocký J, Khudanpur S (2010) Recurrent neural network based language model. In Eleventh annual conference of the international speech communication association

  29. Mikolov T, Sutskever I, Chen K, Corrado G, Dean J (2013) Distributed representations of words and phrases and their compositionality. arXiv preprint arXiv:1310.4546

  30. Morales M, Dey P, Theisen T, Belitz D, Chernova N (2019) An investigation of deep learning systems for suicide risk assessment. In proceedings of the sixth workshop on computational linguistics and clinical psychology (pp. 177-181)

  31. Munikar M, Shakya S, Shrestha A (2019) Fine-grained sentiment classification using BERT. In 2019 artificial intelligence for transforming business and society (AITB) (Vol. 1, pp. 1-5). IEEE

  32. Nordin N, Zainol Z, Mohd Noor MH, Lai Fong C (2021) A comparative study of machine learning techniques for suicide attempts predictive model. Health Inform J 27(1):1460458221989395

    Article  Google Scholar 

  33. Onan A (2019) Topic-enriched word embeddings for sarcasm identification. In computer science on-line conference (pp. 293-304). Springer, Cham

  34. Pestian J, Matykiewicz P, Grupp-Phelan J, Lavanier SA, Combs J, Kowatch R (2008) Using natural language processing to classify suicide notes. In proceedings of the workshop on current trends in biomedical natural language processing (pp. 96-97)

  35. Pompili M, Innamorati M, Di Vittorio C, Sher L, Girardi P, Amore M (2014) Sociodemographic and clinical differences between suicide ideators and attempters: a study of mood disordered patients 50 years and older. Suicide Life Threat Behav 44(1):34–45

    Article  Google Scholar 

  36. Rajesh Kumar E, Rama Rao KVSN, Nayak SR, Chandra R (2020) Suicidal ideation prediction in twitter data using machine learning techniques. J Interdiscip Mathema 23(1):117–125

    Article  Google Scholar 

  37. Sawhney R, Manchanda P, Mathur P, Shah R, Singh R (2018) Exploring and learning suicidal ideation connotations on social media with deep learning. In proceedings of the 9th workshop on computational approaches to subjectivity, sentiment and social media analysis (pp. 167-175)

  38. Sawhney R, Manchanda P, Singh R, Aggarwal S (2018) A computational approach to feature extraction for identification of suicidal ideation in tweets. In proceedings of ACL 2018, student research workshop (pp. 91-98)

  39. Schapire RE, Singer Y, Singhal A (1998). Boosting and Rocchio applied to text filtering. In proceedings of the 21st annual international ACM SIGIR conference on research and development in information retrieval (pp. 215-223)

  40. Silver MA, Bohnert M, Beck AT, Marcus D (1971) Relation of depression of attempted suicide and seriousness of intent. Arch Gen Psychiatry 25(6):573–576

    Article  Google Scholar 

  41. Sinha PP, Mishra R, Sawhney R, Mahata D, Shah RR, Liu H (2019) # Suicidal-a multipronged approach to identify and explore suicidal ideation in twitter. In proceedings of the 28th ACM international conference on information and knowledge management (pp. 941-950)

  42. Sosa PM (2017) Twitter sentiment analysis using combined LSTM-CNN models. Eprint Arxiv, 1-9

  43. Sun C, Huang L, Qiu X (2019) Utilizing BERT for aspect-based sentiment analysis via constructing auxiliary sentence. In proceedings of the 2019 conference of the north American chapter of the Association for Computational Linguistics: human language technologies, volume 1 (Long and short papers) (pp. 380-385)

  44. Tadesse MM, Lin H, Xu B, Yang L (2020) Detection of suicide ideation in social media forums using deep learning. Algorithms 13(1):7

    Article  Google Scholar 

  45. Wang Z, Qian X (2008) Text categorization based on LDA and SVM. In 2008 international conference on computer science and software engineering (Vol. 1, pp. 674-677). IEEE

  46. Weng JC, Lin TY, Tsai YH, Cheok MT, Chang YPE, Chen VCH (2020) An autoencoder and machine learning model to predict suicidal ideation with brain structural imaging. J Clin Med 9(3):658

    Article  Google Scholar 

  47. World Health Organization. (2018) National suicide prevention strategies: Progress, examples and indicators

  48. World Health Organization (2018) National suicide prevention strategies: Progress, examples and indicators

  49. Xu B, Wang N, Chen T, Li M (2015) Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853

  50. Yang Y, Zheng L, Zhang J, Cui Q, Li Z, Yu PS (2018) TI-CNN: convolutional neural networks for fake news detection. arXiv preprint arXiv:1806.00749

  51. Yin W, Schütze H (2016) Multichannel variable-size convolution for sentence classification. arXiv preprint arXiv:1603.04513

  52. Zeiler MD., Ranzato M, Monga R, Mao M, Yang K, Le QV, ..., Hinton GE (2013 On rectified linear units for speech processing. In 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 3517–3521). IEEE

  53. Zhang, Y, Wallace B (2015) A sensitivity analysis of (and practitioners' guide to) convolutional neural networks for sentence classification. arXiv preprint arXiv:1510.03820

  54. Zhang X, Zhao J, Lecun Y (2015) Character-level convolutional networks for text classification. Adv Neural Inf Proces Syst 2015:649–657

    Google Scholar 

  55. Zhang, J.; Li, Y.; Tian, J.; Li T (2018) LSTM-CNN Hybrid Model for Text Classification. In Proceedings of the 2018 IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), Chongqing, China: pp. 1675

  56. Zhu H, Xia X, Yao J, Fan H, Wang Q, Gao Q (2020) Comparisons of different classification algorithms while using text mining to screen psychiatric inpatients with suicidal behaviors. J Psychiatr Res 124:123–130

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Computer Science Department, Bharati Vidyapeeth’s College of Engineering, New Delhi, India

    Bhavini Priyamvada, Shruti Singhal, Priya Goel, Mehar Rani & Muskan Srivastava

  2. Graduate School, Duy Tan University, Da Nang, 550000, Viet Nam

    Anand Nayyar

  3. Faculty of Information Technology, Duy Tan University, Da Nang, 550000, Viet Nam

    Anand Nayyar

  4. Information Technology Department, Bhagwan Parshuram Institute of Technology, New Delhi, India

    Rachna Jain

Authors
  1. Bhavini Priyamvada
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shruti Singhal
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Anand Nayyar
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Rachna Jain
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Priya Goel
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Mehar Rani
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Muskan Srivastava
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Anand Nayyar.

Ethics declarations

Conflict of interest

The Authors declare that there is no conflict of interest.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Priyamvada, B., Singhal, S., Nayyar, A. et al. Stacked CNN - LSTM approach for prediction of suicidal ideation on social media. Multimed Tools Appl 82, 27883–27904 (2023). https://doi.org/10.1007/s11042-023-14431-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-023-14431-z

Keywords

Search

Navigation