Skip to main content
Springer Nature Link
Log in

The Improved Depression Recovery Motivation Recommendation System (I-DRMRS) in Online Social Networks

  • Original Research
  • Published:
SN Computer Science Aims and scope Submit manuscript

Abstract

It is evident that the Online Social Network (OSN) has become a platform to express human emotions. The proposed Improved Depression Recovery Motivation Recommendation System (I-DRMRS) monitors people in depression through OSN posts and accelerates the life-saving process. The research objectives of the I-DRMRS are reducing the suicidal death rate, improving the prediction accuracy, reducing the False Positive (FP) rate and accelerating the process of identifying the suicidal (sybil) thought people. The I-DRMRS consists of three tasks. Task-1: clustering—location-based clustering and assigning the psychiatrists for every cluster, Task-2: classification—consists of both the rigorously trained TensorFlow (TF) image and the TensorFlow (TF) text classifier to detect suicidal thinking person’s considering the images and texts they post in OSN on a daily basis as {suicidal—‘s’, non-suicidal—‘ns’}. Task-3: motivator module (M-Module) and Alarm FOaF—the result of the classifier module is given as feedback to the psychiatrists assigned to each cluster. Psychiatrists motivate the suicidal thought person for a time period T, and monitor emotion shifts. The alarm is given to the suicidal thought person’s Friend Of a Friend (FOaF) if no improvement is monitored by psychiatrists even after the M-Module has been implemented. The Facebook dataset extracted by the beautiful soup (Python) is used. The performance analysis shows 97% accuracy, 1% false positive (FP) rate, 0% false negative (FN) rate, 95% true positive (TP) rate and 98.7% true negative (TN) rate.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Similar content being viewed by others

Availability of Data and Material

My Manuscript has associated data in the data repository.

Code Availability

Our research uses own coding.

References

  1. Chiu CY, Lane HY, Koh JL, Chen ALP. Multimodal depression detection on instagram considering time interval of posts. J Intell Inf Syst. 2020. https://doi.org/10.1007/s10844-020-00599-5.

    Article  Google Scholar 

  2. Brailovskaia J, Forkmann T, Glaesmer H, Paashaus L, Rath D, Schönfelder A, Juckel G, Teismann T. Positive mental health moderates the association between suicide ideation and suicide attempts. J Affect Disord. 2019;245:246–9. https://doi.org/10.1016/j.jad.2018.11.005.

    Article  Google Scholar 

  3. Burke TA, Ammerman BA, Jacobucci R. The use of machine learning in the study of suicidal and non-suicidal self-injurious thoughts and behaviors: a systematic review. J Affect Disord. 2019;245:869–84. https://doi.org/10.1016/j.jad.2018.11.073.

    Article  Google Scholar 

  4. Kadhim AI. Survey on supervised machine learning techniques for automatic text classification. Artif Intell Rev. 2019;52:273–92. https://doi.org/10.1007/s10462-018-09677-1.

    Article  Google Scholar 

  5. Pohl D, Bouchachia A, Hellwagner H. Social media for crisis management: clustering approaches for sub-event detection. Multimed Tools Appl. 2015;74:3901–32. https://doi.org/10.1007/s11042-013-1804-2.

    Article  Google Scholar 

  6. Bai S, Hao B, Li A, Yuan S, Gao R, Zhu T. Predicting big five personality traits of microblog people. In: IEEE/WIC/ACM International Conferences on Web Intelligence (WI) and Intelligent Agent Technology (IAT). IEEE; 2013. https://doi.org/10.1109/WI-IAT.2013.70.

  7. Servi L, Elson SB. A mathematical approach to gauging influence by identifying shifts in the emotions of social media people. IEEE Trans Comput Soc Syst. 2014. https://doi.org/10.1109/TCSS.2014.2384216.

    Article  Google Scholar 

  8. Wang X, Jia J, Tang J, Boya W, Cai L, Xie L. Modeling emotion influence in image social networks. IEEE Trans Affect Comput. 2015;6(3):286–97. https://doi.org/10.1109/TAFFC.2015.2400917.

    Article  Google Scholar 

  9. Chomutare T. Text classification to automatically identify online patients vulnerable to depression. In: Pervasive computing paradigms for mental health, lecture notes of the institute for computer sciences, social informatics and telecommunications engineering, vol. 100. Cham: Springer; 2014. p. 125–30. https://doi.org/10.1007/978-3-319-11564-1_13.

    Chapter  Google Scholar 

  10. Rajesh Kumar E, Rama Rao KVSN, Nayak SR, Chandra R. Suicidal ideation prediction in twitter data using machine learning techniques. J Interdiscip Math. 2020;23(1):117–25. https://doi.org/10.1080/09720502.2020.1721674.

    Article  Google Scholar 

  11. Bouachir W, Noumeir R. Automated video surveillance for preventing suicide attempts. In: 7th International Conference on Imaging for Crime Detection and Prevention (ICDP 2016), Madrid. IET Digital Library; 2016. p. 1–6. https://doi.org/10.1049/ic.2016.0081.

  12. Wang Y, Tang J, Li J, Li B, Wan Y, Mellina C, O’Hare N, Chang Y. Understanding and discovering deliberate self-harm content in social media. In: International World Wide Web Conference Committee (IW3C2). ACM Digital Library; 2017. p. 93–102. https://doi.org/10.1145/3038912.3052555.

  13. Notredame C-E, Morgiève M, Morel F, Berrouiguet S, Azé J, Vaiva G. Distress, suicidality, and affective disorders at the time of social networks. Curr Psychiatry Rep. 2019;21:98. https://doi.org/10.1007/s11920-019-1087-z.

    Article  Google Scholar 

  14. Chu SH, Lenglet C, Schreiner MW, Klimes-Dougan B, Cullen K, Parhi KK. Anatomical biomarkers for adolescent major depressive disorder from diffusion weighted imaging using SVM classifier. Conf Proc IEEE Eng Med Biol Soc. 2018;2018(2018):2740–3. https://doi.org/10.1109/EMBC.2018.8512852,IEEE.

    Article  Google Scholar 

  15. De Choudhury M, Gamon M, Counts S, Horvitz E. Predicting depression via social media. In: Association for the advancement of artificial intelligence. 2013.

  16. Notredame C-E, Grandgenèvre P, Pauwels N, Morgiève M, Wathelet M, Vaiva G, Séguin M. Leveraging the web and social media to promote access to care among suicidal individuals. Front Psychol. 2018;9:1338. https://doi.org/10.3389/fpsyg.2018.01338.

    Article  Google Scholar 

  17. Burdisso SG, Errecalde M, Montes-y-Gómez M. A text classification framework for simple and effective early depression detection over social media streams. Expert Syst Appl. 2019;133:182–97. https://doi.org/10.1016/j.eswa.2019.05.023.

    Article  Google Scholar 

  18. Gibson K, Trnka S. Young people’s priorities for support on social media: “It takes trust to talk about these issues.” Comput Hum Behav. 2020;102:238–47. https://doi.org/10.1016/j.chb.2019.08.030.

    Article  Google Scholar 

  19. Wagner B, Keller V, Knaevelsrud C, Maercker A. Social acknowledgement as a predictor of post-traumatic stress and complicated grief after witnessing assisted suicide. Int J Soc Psychiatry. 2015;58(4):381–5. https://doi.org/10.1177/0020764011400791,Sagepublication.

    Article  Google Scholar 

  20. Li L, Wang Z, Zhang Q, Wen H. Effect of anger, anxiety, and sadness on the propagation scale of social media posts after natural disasters. Inf Process Manag. 2020. https://doi.org/10.1016/j.ipm.2020.102313.

    Article  Google Scholar 

  21. Shen H, Lin Y, Sapra K, Li Z. Enhancing collusion resilience in reputation systems. IEEE Trans Parallel Distrib Syst. 2015;27(8):2274–87. https://doi.org/10.1109/TPDS.2015.2489198.

    Article  Google Scholar 

  22. Deng S, Huang L, Xu G, Wu X, Wu Z. On deep learning for trust-aware recommendations in social networks. IEEE Trans Neural Netw Learn Syst. 2017;28(5):1164–77. https://doi.org/10.1109/TNNLS.2016.2514368.

    Article  Google Scholar 

  23. Bollena J, Maoa H, Zengb X. Twitter mood predicts the stock market. J Comput Sci. 2011;2(1):1–8. https://doi.org/10.1016/j.jocs.2010.12.007.

    Article  Google Scholar 

  24. Davoudi A, Chatterjee M. Product rating prediction using centrality measures in social networks. In: 2015 36th IEEE Sarnoff Symposium, Newark, NJ, 2015. IEEE; 2015. p. 94–8. https://doi.org/10.1109/SARNOF.2015.7324650.

  25. Selva kumar S, Kayarvizhy N, Sailaja Kumar K. Analysis of information propagation in academic social networks. In: 2016 International Conference on Recent Trends in Information Technology (ICRTIT), Chennai, 2016. IEEE; 2016. p. 1–4. https://doi.org/10.1109/ICRTIT.2016.7569575.

  26. Li F, He Y, Niu B, Li H, Wang H. Match-MORE: an efficient private matching scheme using friends-of-friends’ recommendation. In: 2016 International Conference on Computing, Networking and Communications (ICNC), Kauai, HI, 2016. IEEE; 2016. p. 1–6. https://doi.org/10.1109/ICCNC.2016.7440630.

  27. Guo L, Zhang C, Fang Y. A trust-based privacy-preserving friend recommendation scheme for online social networks. IEEE Trans Depend Secure Comput. 2015;12(4):413–27. https://doi.org/10.1109/TDSC.2014.2355824.

    Article  Google Scholar 

  28. He D, Kumar N, Wang H, Wang L, Choo K-KR, Vinel A. A provably-secure cross-domain handshake scheme with symptoms-matching for mobile healthcare social network. IEEE Trans Depend Secure Comput. 2018;15(4):633–45. https://doi.org/10.1109/TDSC.2016.2596286.

    Article  Google Scholar 

  29. Laniado D, Volkovich Y, Scellato S, Mascolo C, Kaltenbrunner A. The impact of geographic distance on online social interactions. Inf Syst Front. 2018;20:1203–18. https://doi.org/10.1007/s10796-017-9784-9.

    Article  Google Scholar 

  30. Losada DE, Crestani F. A test collection for research on depression and language use. In: International Conference of the Cross-Language Evaluation Forum for European Languages. Springer; 2016. p. 28–39. http://doi-org-443.webvpn.fjmu.edu.cn/10.1007/978-3-319-44564-9_3.

  31. Losada DE, Crestani F, Parapar J. erisk 2017: Clef lab on early risk prediction on the internet: experimental foundations. In: International Conference of the Cross-Language Evaluation Forum for European Languages, Springer; 2017. p. 346–360. http://doi-org-443.webvpn.fjmu.edu.cn/10.1007/978-3-030-58219-7_20.

  32. Torous J, Larsen ME, Depp C, Cosco TD, Barnett I, Nock MK, Firth J. Smart phones, sensors, and machine learning to advance real-time prediction and interventions for suicide prevention: a review of current progress and next steps. Curr Psychiatry Rep. 2018;20:51. https://doi.org/10.1007/s11920-018-0914-y.

    Article  Google Scholar 

  33. Yasir Arafat SM, Mali B, Akter H. Demography and risk factors of suicidal behavior in Bangladesh: a retrospective online news content analysis. Asian J Psychiatry. 2018;36:96–9. https://doi.org/10.1016/j.ajp.2018.07.008.

    Article  Google Scholar 

  34. Bailey E, Rice S, Robinson J, Kovi MN, Alvarez-Jimenez M. Theoretical and empirical foundations of a novel online social networking intervention for youth suicide prevention: a conceptual review. J Affect Disord. 2018;238:499–505.

    Article  Google Scholar 

Download references

Funding

No funding was received to assist with the preparation of this manuscript.

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, SRM Valliammai Engineering College, Kattankulathur, Kancheepuram (Dist.), Tamil Nadu, 603203, India

    Poornima Nedunchezhian

  2. Department of Electronics and Communication Engineering, SRM Valliammai Engineering College, Kattankulathur, Kancheepuram (Dist.), Tamil Nadu, 603203, India

    Murugan Mahalingam

Authors
  1. Poornima Nedunchezhian
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Murugan Mahalingam
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

First author has collected the data and pre-processed for efficient functionality and executed location-based clustering task and classification task. Second author has executed M-Module and alarm task and integrated it with the other two modules.

Corresponding author

Correspondence to Poornima Nedunchezhian.

Ethics declarations

Conflict of interest

The authors have no conflict of interest.

Ethics approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Consent to participate

Not applicable.

Consent for publication

We approve for publication.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Nedunchezhian, P., Mahalingam, M. The Improved Depression Recovery Motivation Recommendation System (I-DRMRS) in Online Social Networks. SN COMPUT. SCI. 3, 166 (2022). https://doi.org/10.1007/s42979-022-01047-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s42979-022-01047-7

Keywords